mirror of
https://github.com/apache/impala.git
synced 2026-01-10 09:00:16 -05:00
0d2919fe7f
This patch cleans up analysis and execution of scalar and aggregate functions so that there is no difference between how builtins and user functions are handled. The only difference is that the catalog is populated with the builtins all the time. The BE always gets a TFunction object and just executes it (builtins will have an empty hdfs file location). This removes the opcode registry and all of the functionality is subsumed by the catalog, most of which was already duplicated there anyway. This also introduces the concept of a system database; databases that the user cannot modify and is populated automatically on startup. Change-Id: Iaa3f84dad0a1a57691f5c7d8df7305faf01d70ed Reviewed-on: http://gerrit.ent.cloudera.com:8080/1386 Reviewed-by: Nong Li <nong@cloudera.com> Tested-by: jenkins Reviewed-on: http://gerrit.ent.cloudera.com:8080/1577
498 lines
14 KiB
Plaintext
498 lines
14 KiB
Plaintext
# full scan of string typed row-key
|
|
select * from functional_hbase.stringids
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
====
|
|
# predicate on row key doesn't get transformed into scan parameter, because
|
|
# it's mapped as an int (but stored in ascii and ordered lexicographically)
|
|
select * from functional_hbase.alltypessmall
|
|
where id < 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: id < 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: id < 5
|
|
====
|
|
# if the row key is mapped as a string col, range predicates are applied to the scan
|
|
select * from functional_hbase.stringids
|
|
where id = '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 5:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id > '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 5\0:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id >= '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 5:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id < '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:5
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id <= '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id > '4' and id < '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4\0
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4\0:5
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4\0
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id >= '4' and id < '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4:5
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id > '4' and id <= '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4\0
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4\0:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4\0
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
select * from functional_hbase.stringids
|
|
where id >= '4' and id <= '5'
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
# with aggregation
|
|
select int_col, count(*)
|
|
from functional_hbase.alltypessmall
|
|
where id < 5
|
|
group by 1
|
|
---- PLAN
|
|
01:AGGREGATE [FINALIZE]
|
|
| output: count(*)
|
|
| group by: int_col
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: id < 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
04:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
03:AGGREGATE [MERGE FINALIZE]
|
|
| output: sum(count(*))
|
|
| group by: int_col
|
|
|
|
|
02:EXCHANGE [PARTITION=HASH(int_col)]
|
|
|
|
|
01:AGGREGATE
|
|
| output: count(*)
|
|
| group by: int_col
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: id < 5
|
|
====
|
|
# predicates on string columns against a constant string are converted to HBase filters
|
|
select * from functional_hbase.alltypessmall where string_col = '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col EQUAL '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col EQUAL '4'
|
|
====
|
|
# test all comparison ops
|
|
select * from functional_hbase.alltypessmall where string_col != '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col NOT_EQUAL '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col NOT_EQUAL '4'
|
|
====
|
|
select * from functional_hbase.alltypessmall where string_col < '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col LESS '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col LESS '4'
|
|
====
|
|
select * from functional_hbase.alltypessmall where string_col > '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col GREATER '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col GREATER '4'
|
|
====
|
|
select * from functional_hbase.alltypessmall where string_col <= '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col LESS_OR_EQUAL '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col LESS_OR_EQUAL '4'
|
|
====
|
|
select * from functional_hbase.alltypessmall where string_col >= '4'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col GREATER_OR_EQUAL '4'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col GREATER_OR_EQUAL '4'
|
|
====
|
|
# test multiple filters
|
|
select * from functional_hbase.alltypessmall
|
|
where string_col >= '4' and string_col != '2' and date_string_col = '04/03/09'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters:
|
|
d:date_string_col EQUAL '04/03/09'
|
|
d:string_col GREATER_OR_EQUAL '4'
|
|
d:string_col NOT_EQUAL '2'
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters:
|
|
d:date_string_col EQUAL '04/03/09'
|
|
d:string_col GREATER_OR_EQUAL '4'
|
|
d:string_col NOT_EQUAL '2'
|
|
====
|
|
# mix of predicates and functional_hbase. filters
|
|
select * from functional_hbase.alltypessmall where string_col = '4' and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
====
|
|
# mix of predicates, functional_hbase. filters and start/stop keys
|
|
select * from functional_hbase.stringids
|
|
where string_col = '4' and tinyint_col = 5 and id >= '4' and id <= '5'
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
====
|
|
# predicates involving casts (ie, non-string comparisons) cannot be turned into filters
|
|
select * from functional_hbase.alltypessmall where cast(string_col as int) >= 4
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: CAST(string_col AS INT) >= 4
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: CAST(string_col AS INT) >= 4
|
|
====
|
|
# non-const comparisons cannot be turned into filters
|
|
select * from functional_hbase.alltypessmall where string_col >= date_string_col
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: string_col >= date_string_col
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.alltypessmall]
|
|
predicates: string_col >= date_string_col
|
|
====
|
|
# IMP-1188 - row key predicate is a constant expr.
|
|
select * from functional_hbase.stringids
|
|
where id = concat('', '5')
|
|
and tinyint_col = 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 5:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 5
|
|
stop key: 5\0
|
|
predicates: tinyint_col = 5
|
|
====
|
|
# IMP-1188 - row key predicate is a constant expr.
|
|
select * from functional_hbase.stringids
|
|
where string_col = '4' and tinyint_col = 5
|
|
and id >= concat('', '4') and id <= concat('5', '')
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60202 4:5\0
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
start key: 4
|
|
stop key: 5\0
|
|
hbase filters: d:string_col EQUAL '4'
|
|
predicates: tinyint_col = 5
|
|
====
|
|
# IMP-1188 - row key predicate is null.
|
|
select * from functional_hbase.stringids where id = null
|
|
---- PLAN
|
|
empty scan node
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
empty scan node
|
|
====
|
|
# IMP-1188 - row key lower bound is bigger than upper bound.
|
|
select * from functional_hbase.stringids where id > 'b' and id < 'a'
|
|
---- PLAN
|
|
empty scan node
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
empty scan node
|
|
====
|
|
# IMP-1188 - casting row key to non-string type disables predicate from being pushed
|
|
# into HBase
|
|
select * from functional_hbase.stringids
|
|
where cast(id as int) < 5
|
|
---- PLAN
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
predicates: CAST(id AS INT) < 5
|
|
---- SCANRANGELOCATIONS
|
|
NODE 0:
|
|
HBASE KEYRANGE port=60201 <unbounded>:3
|
|
HBASE KEYRANGE port=60202 3:7
|
|
HBASE KEYRANGE port=60203 7:<unbounded>
|
|
---- DISTRIBUTEDPLAN
|
|
01:EXCHANGE [PARTITION=UNPARTITIONED]
|
|
|
|
|
00:SCAN HBASE [functional_hbase.stringids]
|
|
predicates: CAST(id AS INT) < 5
|
|
====
|