jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2026-01-02 12:00:33 -05:00
Code Issues Projects Releases Wiki Activity
Files
e39de943162af93f59f366ba42b6da7aa2f0c2aa
impala/testdata/workloads/functional-query/queries/QueryTest/insert.test
Nong Li a3bc1ce133 Some parquet encoder/decoder refactoring. Added dictionary to other types. 
Split out the encoder/type for parquet reader/writer. I think this puts us
in a better place to support future encodings.

On the tpch lineitem table, the results are:
Before:
  BytesWritten: 236.45 MB
  Per Column Sizes:
    l_comment: 75.71 MB
    l_commitdate: 8.64 MB
    l_discount: 11.19 MB
    l_extendedprice: 33.02 MB
    l_linenumber: 4.56 MB
    l_linestatus: 869.98 KB
    l_orderkey: 8.99 MB
    l_partkey: 27.02 MB
    l_quantity: 11.58 MB
    l_receiptdate: 8.65 MB
    l_returnflag: 1.40 MB
    l_shipdate: 8.65 MB
    l_shipinstruct: 1.45 MB
    l_shipmode: 2.17 MB
    l_suppkey: 21.91 MB
    l_tax: 10.68 MB
After:
 BytesWritten: 198.63 MB            (84%)
  Per Column Sizes:
    l_comment: 75.71 MB             (100%)
    l_commitdate: 8.64 MB           (100%)
    l_discount: 2.89 MB             (25.8%)
    l_extendedprice: 33.13 MB       (100.33%)
    l_linenumber: 1.50 MB           (32.89%)
    l_linestatus: 870.26 KB         (100.032%)
    l_orderkey: 9.18 MB             (102.11%)
    l_partkey: 27.10 MB             (100.29%)
    l_quantity: 4.32 MB             (37.31%)
    l_receiptdate: 8.65 MB          (100%)
    l_returnflag: 1.40 MB           (100%)
    l_shipdate: 8.65 MB             (100%)
    l_shipinstruct: 1.45 MB         (100%)
    l_shipmode: 2.17 MB             (100%)
    l_suppkey: 10.11 MB             (46.14%)
    l_tax: 2.89 MB                  (27.06%)

The table is overall 84% as big (i.e. 16% smaller). A few columns got marginally
bigger. If the file filled  the 1 GB, I'd expect the overhead to decrease even
more.

The restructuring to use a virtual call doesn't seem to change things much and
will go away when we codegen the scanner.

Here's what they look like with this patch (note this is on the before data files,
so only string cols are dictionary encoded).

Before query times:
  Insert Time: 8.5 sec
  select *: 2.3 sec
  select avg(l_orderkey): .33 sec

After query times:
  Insert Time: 9.5 sec                  <-- Longer due to doing dictionary encoding
  select *: 2.4 sec                     <-- kind of noisy, possibly a slight slow down
  select avg(l_orderkey): .33 sec

Change-Id: I213fdca1bb972cc200dc0cd9fb14b77a8d36d9e6
Reviewed-on: http://gerrit.ent.cloudera.com:8080/238
Tested-by: jenkins <kitchen-build@cloudera.com>
Reviewed-by: Skye Wanderman-Milne <skye@cloudera.com>
2014-01-08 10:52:16 -08:00

658 lines
25 KiB
Plaintext
Raw Blame History

====
---- QUERY
# insert overwrite unpartitioned table
insert overwrite table alltypesnopart_insert
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
from alltypessmall
where year=2009 and month=04
---- SETUP
RESET alltypesnopart_insert
RELOAD alltypesnopart_insert
---- RESULTS
: 25
====
---- QUERY
# search the overwritten table to verify the results
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col,
double_col, date_string_col, string_col
from alltypesnopart_insert
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string
---- RESULTS
75,false,0,0,0,0,0,0,'04/01/09','0'
76,true,1,1,1,10,1.100000023841858,10.1,'04/01/09','1'
77,false,2,2,2,20,2.200000047683716,20.2,'04/01/09','2'
78,true,3,3,3,30,3.299999952316284,30.3,'04/01/09','3'
79,false,4,4,4,40,4.400000095367432,40.4,'04/01/09','4'
80,true,5,5,5,50,5.5,50.5,'04/01/09','5'
81,false,6,6,6,60,6.599999904632568,60.6,'04/01/09','6'
82,true,7,7,7,70,7.699999809265137,70.7,'04/01/09','7'
83,false,8,8,8,80,8.800000190734863,80.8,'04/01/09','8'
84,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/01/09','9'
85,false,0,0,0,0,0,0,'04/02/09','0'
86,true,1,1,1,10,1.100000023841858,10.1,'04/02/09','1'
87,false,2,2,2,20,2.200000047683716,20.2,'04/02/09','2'
88,true,3,3,3,30,3.299999952316284,30.3,'04/02/09','3'
89,false,4,4,4,40,4.400000095367432,40.4,'04/02/09','4'
90,true,5,5,5,50,5.5,50.5,'04/02/09','5'
91,false,6,6,6,60,6.599999904632568,60.6,'04/02/09','6'
92,true,7,7,7,70,7.699999809265137,70.7,'04/02/09','7'
93,false,8,8,8,80,8.800000190734863,80.8,'04/02/09','8'
94,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/02/09','9'
95,false,0,0,0,0,0,0,'04/03/09','0'
96,true,1,1,1,10,1.100000023841858,10.1,'04/03/09','1'
97,false,2,2,2,20,2.200000047683716,20.2,'04/03/09','2'
98,true,3,3,3,30,3.299999952316284,30.3,'04/03/09','3'
99,false,4,4,4,40,4.400000095367432,40.4,'04/03/09','4'
====
---- QUERY
# insert into unpartitioned table
insert into table alltypesnopart_insert
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
from alltypessmall
where year=2009 and month=04
---- SETUP
RESET alltypesnopart_insert
---- RESULTS
: 25
====
---- QUERY
# search the table to verify it contains 25 rows
select count(*) from alltypesnopart_insert
---- TYPES
bigint
---- RESULTS
25
====
---- QUERY
# static partition overwrite
insert overwrite table alltypesinsert
partition (year=2009, month=4)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
from alltypessmall
where year=2009 and month=4
---- SETUP
DROP PARTITIONS alltypesinsert
RESET alltypesinsert
---- RESULTS
year=2009/month=4/: 25
====
---- QUERY
# search the overwritten partition to verify the results
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col,
double_col, date_string_col, string_col
from alltypesinsert
where year=2009 and month=4
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string
---- RESULTS
75,false,0,0,0,0,0,0,'04/01/09','0'
76,true,1,1,1,10,1.100000023841858,10.1,'04/01/09','1'
77,false,2,2,2,20,2.200000047683716,20.2,'04/01/09','2'
78,true,3,3,3,30,3.299999952316284,30.3,'04/01/09','3'
79,false,4,4,4,40,4.400000095367432,40.4,'04/01/09','4'
80,true,5,5,5,50,5.5,50.5,'04/01/09','5'
81,false,6,6,6,60,6.599999904632568,60.6,'04/01/09','6'
82,true,7,7,7,70,7.699999809265137,70.7,'04/01/09','7'
83,false,8,8,8,80,8.800000190734863,80.8,'04/01/09','8'
84,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/01/09','9'
85,false,0,0,0,0,0,0,'04/02/09','0'
86,true,1,1,1,10,1.100000023841858,10.1,'04/02/09','1'
87,false,2,2,2,20,2.200000047683716,20.2,'04/02/09','2'
88,true,3,3,3,30,3.299999952316284,30.3,'04/02/09','3'
89,false,4,4,4,40,4.400000095367432,40.4,'04/02/09','4'
90,true,5,5,5,50,5.5,50.5,'04/02/09','5'
91,false,6,6,6,60,6.599999904632568,60.6,'04/02/09','6'
92,true,7,7,7,70,7.699999809265137,70.7,'04/02/09','7'
93,false,8,8,8,80,8.800000190734863,80.8,'04/02/09','8'
94,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/02/09','9'
95,false,0,0,0,0,0,0,'04/03/09','0'
96,true,1,1,1,10,1.100000023841858,10.1,'04/03/09','1'
97,false,2,2,2,20,2.200000047683716,20.2,'04/03/09','2'
98,true,3,3,3,30,3.299999952316284,30.3,'04/03/09','3'
99,false,4,4,4,40,4.400000095367432,40.4,'04/03/09','4'
====
---- QUERY
# static partition insert$TABLE, test creation of partitions
insert into table alltypesinsert
partition (year=2009, month=4)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
from alltypessmall
where year=2009 and month=4
---- SETUP
DROP PARTITIONS alltypesinsert
---- RESULTS
year=2009/month=4/: 25
====
---- QUERY
# search the partition to verify it contains all 25 rows
select count(*) from alltypesinsert
where year=2009 and month=4
---- TYPES
bigint
---- RESULTS
25
====
---- QUERY
# partially dynamic partition overwrite
insert overwrite table alltypesinsert
partition (year=2009, month)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col, month
from alltypessmall
where year=2009 and month>1 and month<=4
---- SETUP
DROP PARTITIONS alltypesinsert
---- RESULTS
year=2009/month=2/: 25
year=2009/month=3/: 25
year=2009/month=4/: 25
====
---- QUERY
# search the overwritten partition to verify the results
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col,
double_col, date_string_col, string_col
from alltypesinsert
where year=2009 and month>1 and month<=4
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string
---- RESULTS
25,false,0,0,0,0,0,0,'02/01/09','0'
26,true,1,1,1,10,1.100000023841858,10.1,'02/01/09','1'
27,false,2,2,2,20,2.200000047683716,20.2,'02/01/09','2'
28,true,3,3,3,30,3.299999952316284,30.3,'02/01/09','3'
29,false,4,4,4,40,4.400000095367432,40.4,'02/01/09','4'
30,true,5,5,5,50,5.5,50.5,'02/01/09','5'
31,false,6,6,6,60,6.599999904632568,60.6,'02/01/09','6'
32,true,7,7,7,70,7.699999809265137,70.7,'02/01/09','7'
33,false,8,8,8,80,8.800000190734863,80.8,'02/01/09','8'
34,true,9,9,9,90,9.899999618530273,90.90000000000001,'02/01/09','9'
35,false,0,0,0,0,0,0,'02/02/09','0'
36,true,1,1,1,10,1.100000023841858,10.1,'02/02/09','1'
37,false,2,2,2,20,2.200000047683716,20.2,'02/02/09','2'
38,true,3,3,3,30,3.299999952316284,30.3,'02/02/09','3'
39,false,4,4,4,40,4.400000095367432,40.4,'02/02/09','4'
40,true,5,5,5,50,5.5,50.5,'02/02/09','5'
41,false,6,6,6,60,6.599999904632568,60.6,'02/02/09','6'
42,true,7,7,7,70,7.699999809265137,70.7,'02/02/09','7'
43,false,8,8,8,80,8.800000190734863,80.8,'02/02/09','8'
44,true,9,9,9,90,9.899999618530273,90.90000000000001,'02/02/09','9'
45,false,0,0,0,0,0,0,'02/03/09','0'
46,true,1,1,1,10,1.100000023841858,10.1,'02/03/09','1'
47,false,2,2,2,20,2.200000047683716,20.2,'02/03/09','2'
48,true,3,3,3,30,3.299999952316284,30.3,'02/03/09','3'
49,false,4,4,4,40,4.400000095367432,40.4,'02/03/09','4'
50,true,0,0,0,0,0,0,'03/01/09','0'
51,false,1,1,1,10,1.100000023841858,10.1,'03/01/09','1'
52,true,2,2,2,20,2.200000047683716,20.2,'03/01/09','2'
53,false,3,3,3,30,3.299999952316284,30.3,'03/01/09','3'
54,true,4,4,4,40,4.400000095367432,40.4,'03/01/09','4'
55,false,5,5,5,50,5.5,50.5,'03/01/09','5'
56,true,6,6,6,60,6.599999904632568,60.6,'03/01/09','6'
57,false,7,7,7,70,7.699999809265137,70.7,'03/01/09','7'
58,true,8,8,8,80,8.800000190734863,80.8,'03/01/09','8'
59,false,9,9,9,90,9.899999618530273,90.90000000000001,'03/01/09','9'
60,true,0,0,0,0,0,0,'03/02/09','0'
61,false,1,1,1,10,1.100000023841858,10.1,'03/02/09','1'
62,true,2,2,2,20,2.200000047683716,20.2,'03/02/09','2'
63,false,3,3,3,30,3.299999952316284,30.3,'03/02/09','3'
64,true,4,4,4,40,4.400000095367432,40.4,'03/02/09','4'
65,false,5,5,5,50,5.5,50.5,'03/02/09','5'
66,true,6,6,6,60,6.599999904632568,60.6,'03/02/09','6'
67,false,7,7,7,70,7.699999809265137,70.7,'03/02/09','7'
68,true,8,8,8,80,8.800000190734863,80.8,'03/02/09','8'
69,false,9,9,9,90,9.899999618530273,90.90000000000001,'03/02/09','9'
70,true,0,0,0,0,0,0,'03/03/09','0'
71,false,1,1,1,10,1.100000023841858,10.1,'03/03/09','1'
72,true,2,2,2,20,2.200000047683716,20.2,'03/03/09','2'
73,false,3,3,3,30,3.299999952316284,30.3,'03/03/09','3'
74,true,4,4,4,40,4.400000095367432,40.4,'03/03/09','4'
75,false,0,0,0,0,0,0,'04/01/09','0'
76,true,1,1,1,10,1.100000023841858,10.1,'04/01/09','1'
77,false,2,2,2,20,2.200000047683716,20.2,'04/01/09','2'
78,true,3,3,3,30,3.299999952316284,30.3,'04/01/09','3'
79,false,4,4,4,40,4.400000095367432,40.4,'04/01/09','4'
80,true,5,5,5,50,5.5,50.5,'04/01/09','5'
81,false,6,6,6,60,6.599999904632568,60.6,'04/01/09','6'
82,true,7,7,7,70,7.699999809265137,70.7,'04/01/09','7'
83,false,8,8,8,80,8.800000190734863,80.8,'04/01/09','8'
84,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/01/09','9'
85,false,0,0,0,0,0,0,'04/02/09','0'
86,true,1,1,1,10,1.100000023841858,10.1,'04/02/09','1'
87,false,2,2,2,20,2.200000047683716,20.2,'04/02/09','2'
88,true,3,3,3,30,3.299999952316284,30.3,'04/02/09','3'
89,false,4,4,4,40,4.400000095367432,40.4,'04/02/09','4'
90,true,5,5,5,50,5.5,50.5,'04/02/09','5'
91,false,6,6,6,60,6.599999904632568,60.6,'04/02/09','6'
92,true,7,7,7,70,7.699999809265137,70.7,'04/02/09','7'
93,false,8,8,8,80,8.800000190734863,80.8,'04/02/09','8'
94,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/02/09','9'
95,false,0,0,0,0,0,0,'04/03/09','0'
96,true,1,1,1,10,1.100000023841858,10.1,'04/03/09','1'
97,false,2,2,2,20,2.200000047683716,20.2,'04/03/09','2'
98,true,3,3,3,30,3.299999952316284,30.3,'04/03/09','3'
99,false,4,4,4,40,4.400000095367432,40.4,'04/03/09','4'
====
---- QUERY
# partially dynamic partition insert$TABLE, check partition creation
insert into table alltypesinsert
partition (year=2009, month)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col, month
from alltypessmall
where year=2009 and month>=1 and month<4
---- SETUP
DROP PARTITIONS alltypesinsert
---- RESULTS
year=2009/month=1/: 25
year=2009/month=2/: 25
year=2009/month=3/: 25
====
---- QUERY
# search the partitions to verify they contain all 75 rows
select count(id) from alltypesinsert
where year=2009 and month>=1 and month<4
---- TYPES
bigint
---- RESULTS
75
====
---- QUERY
# fully dynamic partition overwrite
insert overwrite table alltypesinsert
partition (year, month)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col, year, month
from alltypessmall
---- SETUP
DROP PARTITIONS alltypesinsert
---- RESULTS
year=2009/month=1/: 25
year=2009/month=2/: 25
year=2009/month=3/: 25
year=2009/month=4/: 25
====
---- QUERY
# search the overwritten partition to verify the results
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col,
double_col, date_string_col, string_col
from alltypesinsert
where year=2009 and month>=1 and month<=4
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string
---- RESULTS
0,true,0,0,0,0,0,0,'01/01/09','0'
1,false,1,1,1,10,1.100000023841858,10.1,'01/01/09','1'
10,true,0,0,0,0,0,0,'01/02/09','0'
11,false,1,1,1,10,1.100000023841858,10.1,'01/02/09','1'
12,true,2,2,2,20,2.200000047683716,20.2,'01/02/09','2'
13,false,3,3,3,30,3.299999952316284,30.3,'01/02/09','3'
14,true,4,4,4,40,4.400000095367432,40.4,'01/02/09','4'
15,false,5,5,5,50,5.5,50.5,'01/02/09','5'
16,true,6,6,6,60,6.599999904632568,60.6,'01/02/09','6'
17,false,7,7,7,70,7.699999809265137,70.7,'01/02/09','7'
18,true,8,8,8,80,8.800000190734863,80.8,'01/02/09','8'
19,false,9,9,9,90,9.899999618530273,90.90000000000001,'01/02/09','9'
2,true,2,2,2,20,2.200000047683716,20.2,'01/01/09','2'
20,true,0,0,0,0,0,0,'01/03/09','0'
21,false,1,1,1,10,1.100000023841858,10.1,'01/03/09','1'
22,true,2,2,2,20,2.200000047683716,20.2,'01/03/09','2'
23,false,3,3,3,30,3.299999952316284,30.3,'01/03/09','3'
24,true,4,4,4,40,4.400000095367432,40.4,'01/03/09','4'
25,false,0,0,0,0,0,0,'02/01/09','0'
26,true,1,1,1,10,1.100000023841858,10.1,'02/01/09','1'
27,false,2,2,2,20,2.200000047683716,20.2,'02/01/09','2'
28,true,3,3,3,30,3.299999952316284,30.3,'02/01/09','3'
29,false,4,4,4,40,4.400000095367432,40.4,'02/01/09','4'
3,false,3,3,3,30,3.299999952316284,30.3,'01/01/09','3'
30,true,5,5,5,50,5.5,50.5,'02/01/09','5'
31,false,6,6,6,60,6.599999904632568,60.6,'02/01/09','6'
32,true,7,7,7,70,7.699999809265137,70.7,'02/01/09','7'
33,false,8,8,8,80,8.800000190734863,80.8,'02/01/09','8'
34,true,9,9,9,90,9.899999618530273,90.90000000000001,'02/01/09','9'
35,false,0,0,0,0,0,0,'02/02/09','0'
36,true,1,1,1,10,1.100000023841858,10.1,'02/02/09','1'
37,false,2,2,2,20,2.200000047683716,20.2,'02/02/09','2'
38,true,3,3,3,30,3.299999952316284,30.3,'02/02/09','3'
39,false,4,4,4,40,4.400000095367432,40.4,'02/02/09','4'
4,true,4,4,4,40,4.400000095367432,40.4,'01/01/09','4'
40,true,5,5,5,50,5.5,50.5,'02/02/09','5'
41,false,6,6,6,60,6.599999904632568,60.6,'02/02/09','6'
42,true,7,7,7,70,7.699999809265137,70.7,'02/02/09','7'
43,false,8,8,8,80,8.800000190734863,80.8,'02/02/09','8'
44,true,9,9,9,90,9.899999618530273,90.90000000000001,'02/02/09','9'
45,false,0,0,0,0,0,0,'02/03/09','0'
46,true,1,1,1,10,1.100000023841858,10.1,'02/03/09','1'
47,false,2,2,2,20,2.200000047683716,20.2,'02/03/09','2'
48,true,3,3,3,30,3.299999952316284,30.3,'02/03/09','3'
49,false,4,4,4,40,4.400000095367432,40.4,'02/03/09','4'
5,false,5,5,5,50,5.5,50.5,'01/01/09','5'
50,true,0,0,0,0,0,0,'03/01/09','0'
51,false,1,1,1,10,1.100000023841858,10.1,'03/01/09','1'
52,true,2,2,2,20,2.200000047683716,20.2,'03/01/09','2'
53,false,3,3,3,30,3.299999952316284,30.3,'03/01/09','3'
54,true,4,4,4,40,4.400000095367432,40.4,'03/01/09','4'
55,false,5,5,5,50,5.5,50.5,'03/01/09','5'
56,true,6,6,6,60,6.599999904632568,60.6,'03/01/09','6'
57,false,7,7,7,70,7.699999809265137,70.7,'03/01/09','7'
58,true,8,8,8,80,8.800000190734863,80.8,'03/01/09','8'
59,false,9,9,9,90,9.899999618530273,90.90000000000001,'03/01/09','9'
6,true,6,6,6,60,6.599999904632568,60.6,'01/01/09','6'
60,true,0,0,0,0,0,0,'03/02/09','0'
61,false,1,1,1,10,1.100000023841858,10.1,'03/02/09','1'
62,true,2,2,2,20,2.200000047683716,20.2,'03/02/09','2'
63,false,3,3,3,30,3.299999952316284,30.3,'03/02/09','3'
64,true,4,4,4,40,4.400000095367432,40.4,'03/02/09','4'
65,false,5,5,5,50,5.5,50.5,'03/02/09','5'
66,true,6,6,6,60,6.599999904632568,60.6,'03/02/09','6'
67,false,7,7,7,70,7.699999809265137,70.7,'03/02/09','7'
68,true,8,8,8,80,8.800000190734863,80.8,'03/02/09','8'
69,false,9,9,9,90,9.899999618530273,90.90000000000001,'03/02/09','9'
7,false,7,7,7,70,7.699999809265137,70.7,'01/01/09','7'
70,true,0,0,0,0,0,0,'03/03/09','0'
71,false,1,1,1,10,1.100000023841858,10.1,'03/03/09','1'
72,true,2,2,2,20,2.200000047683716,20.2,'03/03/09','2'
73,false,3,3,3,30,3.299999952316284,30.3,'03/03/09','3'
74,true,4,4,4,40,4.400000095367432,40.4,'03/03/09','4'
75,false,0,0,0,0,0,0,'04/01/09','0'
76,true,1,1,1,10,1.100000023841858,10.1,'04/01/09','1'
77,false,2,2,2,20,2.200000047683716,20.2,'04/01/09','2'
78,true,3,3,3,30,3.299999952316284,30.3,'04/01/09','3'
79,false,4,4,4,40,4.400000095367432,40.4,'04/01/09','4'
8,true,8,8,8,80,8.800000190734863,80.8,'01/01/09','8'
80,true,5,5,5,50,5.5,50.5,'04/01/09','5'
81,false,6,6,6,60,6.599999904632568,60.6,'04/01/09','6'
82,true,7,7,7,70,7.699999809265137,70.7,'04/01/09','7'
83,false,8,8,8,80,8.800000190734863,80.8,'04/01/09','8'
84,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/01/09','9'
85,false,0,0,0,0,0,0,'04/02/09','0'
86,true,1,1,1,10,1.100000023841858,10.1,'04/02/09','1'
87,false,2,2,2,20,2.200000047683716,20.2,'04/02/09','2'
88,true,3,3,3,30,3.299999952316284,30.3,'04/02/09','3'
89,false,4,4,4,40,4.400000095367432,40.4,'04/02/09','4'
9,false,9,9,9,90,9.899999618530273,90.90000000000001,'01/01/09','9'
90,true,5,5,5,50,5.5,50.5,'04/02/09','5'
91,false,6,6,6,60,6.599999904632568,60.6,'04/02/09','6'
92,true,7,7,7,70,7.699999809265137,70.7,'04/02/09','7'
93,false,8,8,8,80,8.800000190734863,80.8,'04/02/09','8'
94,true,9,9,9,90,9.899999618530273,90.90000000000001,'04/02/09','9'
95,false,0,0,0,0,0,0,'04/03/09','0'
96,true,1,1,1,10,1.100000023841858,10.1,'04/03/09','1'
97,false,2,2,2,20,2.200000047683716,20.2,'04/03/09','2'
98,true,3,3,3,30,3.299999952316284,30.3,'04/03/09','3'
99,false,4,4,4,40,4.400000095367432,40.4,'04/03/09','4'
====
---- QUERY
# fully dynamic partition insert$TABLE, check partition creation
insert into table alltypesinsert
partition (year, month)
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col, year, month
from alltypessmall
---- SETUP
DROP PARTITIONS alltypesinsert
---- RESULTS
year=2009/month=1/: 25
year=2009/month=2/: 25
year=2009/month=3/: 25
year=2009/month=4/: 25
====
---- QUERY
# search the partitions to verify they contain all 100 rows
select count(timestamp_col) from alltypesinsert
where year=2009 and month>=1 and month<=4
---- TYPES
bigint
---- RESULTS
100
====
---- QUERY
# test insert into ... select *
insert into alltypesinsert partition(year, month) select * from alltypessmall
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2009/month=1/: 25
year=2009/month=2/: 25
year=2009/month=3/: 25
year=2009/month=4/: 25
====
---- QUERY
# check size of alltypesinsert to ensure previous insert worked
select count(*) from alltypesinsert
---- TYPES
bigint
---- RESULTS
100
====
---- QUERY
# static partition insert into string-partitioned table with special characters in partition key
INSERT INTO TABLE insert_string_partitioned PARTITION(s2="/\%.") SELECT "value" FROM alltypessmall LIMIT 1;
---- SETUP
RESET insert_string_partitioned
DROP PARTITIONS insert_string_partitioned
---- RESULTS
s2=%2F%5C%25./: 1
====
---- QUERY
# select with unencoded partition key
SELECT * FROM insert_string_partitioned;
---- TYPES
string, string
---- RESULTS
'value','/\%.'
====
---- QUERY
# select with unencoded partition key as column predicate
SELECT * FROM insert_string_partitioned WHERE s2 = "/\%.";
---- TYPES
string, string
---- RESULTS
'value','/\%.'
====
---- QUERY
# static partition insert into string-partitioned table with non-escaped special characters
# (Hive chooses not to escape + and ' ')
INSERT INTO TABLE insert_string_partitioned PARTITION(s2="_.~ +")
SELECT "value" FROM alltypessmall LIMIT 1;
---- SETUP
DROP PARTITIONS insert_string_partitioned
---- RESULTS
s2=_.~ +/: 1
====
---- QUERY
# select with unencoded partition key
SELECT * FROM insert_string_partitioned;
---- TYPES
string, string
---- RESULTS
'value','_.~ +'
====
---- QUERY
# static partition insert into string-partitioned table with empty partition key
INSERT INTO TABLE insert_string_partitioned PARTITION(s2='')
SELECT "value1" FROM alltypessmall LIMIT 1;
---- SETUP
DROP PARTITIONS insert_string_partitioned
---- RESULTS
s2=__HIVE_DEFAULT_PARTITION__/: 1
====
---- QUERY
# dynamic partition insert into string-partitioned table with empty partition key
INSERT INTO TABLE insert_string_partitioned PARTITION(s2)
SELECT "value2","" FROM alltypessmall LIMIT 1;
---- RESULTS
s2=__HIVE_DEFAULT_PARTITION__/: 1
====
---- QUERY
# static partition insert into string-partitioned table with NULL partition key
INSERT INTO TABLE insert_string_partitioned PARTITION(s2=NULL)
SELECT "value3" FROM alltypessmall LIMIT 1;
---- RESULTS
s2=__HIVE_DEFAULT_PARTITION__/: 1
====
---- QUERY
# dynamic partition insert into string-partitioned table with NULL partition key
INSERT INTO TABLE insert_string_partitioned PARTITION(s2)
SELECT "value4",NULL FROM alltypessmall LIMIT 1;
---- RESULTS
s2=__HIVE_DEFAULT_PARTITION__/: 1
====
---- QUERY
# select with empty partition key as predicate should return nothing, because "" is
# mapped to NULL
SELECT * FROM insert_string_partitioned WHERE s2 = "";
---- TYPES
string, string
---- RESULTS
====
---- QUERY
# select with NULL partition key as predicate should return rows
SELECT s1, s2 FROM insert_string_partitioned where s2 is NULL
order by s1 limit 10
---- TYPES
string, string
---- RESULTS
'value1','NULL'
'value2','NULL'
'value3','NULL'
'value4','NULL'
====
---- QUERY
# static partition insert with constant exprs as partition-key values
insert into alltypesinsert partition(year=cast(100*20+10 as int), month=cast(2*2 as int))
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col,
double_col, date_string_col, string_col, timestamp_col from alltypessmall where month = 4
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2010/month=4/: 25
====
---- QUERY
# static partition insert from a constant select
insert into alltypesinsert
partition(year=2010, month=4)
select 100, false, 1, 1, 1, 10,
10.0, 10.0, "02/01/09", "1", cast("2009-02-01 00:01:00" as timestamp)
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2010/month=4/: 1
====
---- QUERY
# dynamic partition insert from a constant select
insert into table alltypesinsert
partition (year, month)
select 200, true, 2, 2, 2, 20,
20.0, 20.0, "02/01/09", "1", cast("2009-02-01 00:02:00" as timestamp), 2010, 4
---- RESULTS
year=2010/month=4/: 1
====
---- QUERY
# verify contents of alltypesinsert
select * from alltypesinsert order by id limit 2
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string, timestamp, int, int
---- RESULTS
100,false,1,1,1,10,10,10,'02/01/09','1',2009-02-01 00:01:00,2010,4
200,true,2,2,2,20,20,20,'02/01/09','1',2009-02-01 00:02:00,2010,4
====
---- QUERY
# static partition insert from values statement
insert into alltypesinsert
partition(year=2010, month=4) values
(1, false, 1, 1, 1, 10, NULL, 10.0, "02/01/09", "1", cast("2009-02-01 00:01:00" as timestamp)),
(2, true, 2, NULL, 2, 20, 20.0, 20.0, "02/02/09", "2", NULL),
(3, false, 3, 3, 3, 30, 30.0, 30.0, "02/03/09", NULL, cast("2009-02-03 00:01:00" as timestamp))
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2010/month=4/: 3
====
---- QUERY
# dynamic partition insert from values statement
insert into table alltypesinsert
partition (year, month) values
(4, true, 4, 4, 4, 40, NULL, 40.0, "02/04/09", "4", cast("2009-02-04 00:01:00" as timestamp), 2010, 4),
(5, false, 5, NULL, 5, 50, 50.0, 50.0, "02/05/09", "5", NULL, 2010, 8),
(6, true, 6, 6, 6, 60, 60.0, 60.0, "02/06/09", NULL, cast("2009-02-06 00:01:00" as timestamp), 2010, 8)
---- RESULTS
year=2010/month=4/: 1
year=2010/month=8/: 2
====
---- QUERY
# verify contents of alltypesinsert
select * from alltypesinsert order by id limit 10
---- RESULTS
1,false,1,1,1,10,NULL,10,'02/01/09','1',2009-02-01 00:01:00,2010,4
2,true,2,NULL,2,20,20,20,'02/02/09','2',NULL,2010,4
3,false,3,3,3,30,30,30,'02/03/09','NULL',2009-02-03 00:01:00,2010,4
4,true,4,4,4,40,NULL,40,'02/04/09','4',2009-02-04 00:01:00,2010,4
5,false,5,NULL,5,50,50,50,'02/05/09','5',NULL,2010,8
6,true,6,6,6,60,60,60,'02/06/09','NULL',2009-02-06 00:01:00,2010,8
---- TYPES
INT, BOOLEAN, TINYINT, SMALLINT, INT, BIGINT, FLOAT, DOUBLE, STRING, STRING, TIMESTAMP, INT, INT
====
---- QUERY
# Test with clause in an insert statement.
with t1 as (select * from alltypestiny)
insert into alltypesinsert partition(year, month) select * from t1
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2009/month=1/: 2
year=2009/month=2/: 2
year=2009/month=3/: 2
year=2009/month=4/: 2
====
---- QUERY
# Test with clause in an insert statement and in its query statement.
with t1 as (select * from alltypestiny)
insert into alltypesinsert partition(year, month)
with t2 as (select * from alltypestiny)
select * from t1 union all select * from t2
---- SETUP
RESET alltypesinsert
RELOAD alltypesinsert
---- RESULTS
year=2009/month=1/: 4
year=2009/month=2/: 4
year=2009/month=3/: 4
year=2009/month=4/: 4
====
---- QUERY
# Test inserting NULLs for all types
insert overwrite table alltypesnopart_insert
select NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL
from alltypessmall limit 10
---- RESULTS
: 10
====
---- QUERY
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
from alltypesnopart_insert
---- TYPES
int, boolean, tinyint, smallint, int, bigint, float, double, string, string, timestamp
---- RESULTS
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL','NULL',NULL
====
Reference in New Issue View Git Blame Copy Permalink