mirror of
https://github.com/apache/impala.git
synced 2026-01-04 00:00:56 -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
164 lines
4.5 KiB
Plaintext
164 lines
4.5 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Tests explaining a query (TPCDS-Q19)
|
|
explain
|
|
select
|
|
i_brand_id,
|
|
i_brand,
|
|
i_manufact_id,
|
|
i_manufact,
|
|
sum(ss_ext_sales_price) ext_price
|
|
from
|
|
tpcds.store_sales
|
|
join tpcds.item on (store_sales.ss_item_sk = item.i_item_sk)
|
|
join tpcds.customer on (store_sales.ss_customer_sk = customer.c_customer_sk)
|
|
join tpcds.customer_address on (customer.c_current_addr_sk = customer_address.ca_address_sk)
|
|
join tpcds.store on (store_sales.ss_store_sk = store.s_store_sk)
|
|
where
|
|
ss_date between '1999-11-01' and '1999-11-30'
|
|
and i_manager_id = 7
|
|
and substr(ca_zip, 1, 5) <> substr(s_zip, 1, 5)
|
|
group by
|
|
i_brand,
|
|
i_brand_id,
|
|
i_manufact_id,
|
|
i_manufact
|
|
order by
|
|
ext_price desc,
|
|
i_brand,
|
|
i_brand_id,
|
|
i_manufact_id,
|
|
i_manufact
|
|
limit 100
|
|
---- RESULTS
|
|
'Estimated Per-Host Requirements: Memory=144.66MB VCores=5'
|
|
''
|
|
'19:TOP-N [LIMIT=100]'
|
|
'| order by: sum(ss_ext_sales_price) DESC, i_brand ASC, i_brand_id ASC, i_manufact_id ASC, i_manufact ASC'
|
|
'|'
|
|
'18:EXCHANGE [PARTITION=UNPARTITIONED]'
|
|
'|'
|
|
'10:TOP-N [LIMIT=100]'
|
|
'| order by: sum(ss_ext_sales_price) DESC, i_brand ASC, i_brand_id ASC, i_manufact_id ASC, i_manufact ASC'
|
|
'|'
|
|
'17:AGGREGATE [MERGE FINALIZE]'
|
|
'| output: sum(sum(ss_ext_sales_price))'
|
|
'| group by: i_brand, i_brand_id, i_manufact_id, i_manufact'
|
|
'|'
|
|
'16:EXCHANGE [PARTITION=HASH(i_brand,i_brand_id,i_manufact_id,i_manufact)]'
|
|
'|'
|
|
'09:AGGREGATE'
|
|
'| output: sum(ss_ext_sales_price)'
|
|
'| group by: i_brand, i_brand_id, i_manufact_id, i_manufact'
|
|
'|'
|
|
'08:HASH JOIN [INNER JOIN, BROADCAST]'
|
|
'| hash predicates: store_sales.ss_store_sk = store.s_store_sk'
|
|
'| other predicates: substr(ca_zip, 1, 5) != substr(s_zip, 1, 5)'
|
|
'|'
|
|
'|--15:EXCHANGE [BROADCAST]'
|
|
'| |'
|
|
'| 04:SCAN HDFS [tpcds.store]'
|
|
'| partitions=1/1 size=3.08KB'
|
|
'|'
|
|
'07:HASH JOIN [INNER JOIN, BROADCAST]'
|
|
'| hash predicates: store_sales.ss_item_sk = item.i_item_sk'
|
|
'|'
|
|
'|--14:EXCHANGE [BROADCAST]'
|
|
'| |'
|
|
'| 01:SCAN HDFS [tpcds.item]'
|
|
'| partitions=1/1 size=4.82MB'
|
|
'| predicates: i_manager_id = 7'
|
|
'|'
|
|
'06:HASH JOIN [INNER JOIN, BROADCAST]'
|
|
'| hash predicates: customer.c_customer_sk = store_sales.ss_customer_sk'
|
|
'|'
|
|
'|--13:EXCHANGE [BROADCAST]'
|
|
'| |'
|
|
'| 00:SCAN HDFS [tpcds.store_sales]'
|
|
'| partitions=2/120 size=663.52KB'
|
|
'|'
|
|
'05:HASH JOIN [INNER JOIN, PARTITIONED]'
|
|
'| hash predicates: customer_address.ca_address_sk = customer.c_current_addr_sk'
|
|
'|'
|
|
'|--12:EXCHANGE [PARTITION=HASH(customer.c_current_addr_sk)]'
|
|
'| |'
|
|
'| 02:SCAN HDFS [tpcds.customer]'
|
|
'| partitions=1/1 size=12.60MB'
|
|
'|'
|
|
'11:EXCHANGE [PARTITION=HASH(customer_address.ca_address_sk)]'
|
|
'|'
|
|
'03:SCAN HDFS [tpcds.customer_address]'
|
|
' partitions=1/1 size=5.25MB'
|
|
====
|
|
---- QUERY
|
|
# Tests explaining an insert query
|
|
explain insert overwrite functional.alltypessmall (id, string_col)
|
|
partition (year, month)
|
|
select a.id, a.string_col, a.year, a.month from functional.alltypes a
|
|
left semi join functional.alltypesagg b on (a.id = b.id)
|
|
where a.year > 2009 and a.month = 4
|
|
union distinct
|
|
select id, string_col, year, month from functional.alltypes
|
|
---- RESULTS
|
|
'Estimated Per-Host Requirements: Memory=192.01MB VCores=3'
|
|
''
|
|
'WRITE TO HDFS [functional.alltypessmall, OVERWRITE=true, PARTITION-KEYS=(year,month)]'
|
|
'| partitions=96'
|
|
'|'
|
|
'05:AGGREGATE [FINALIZE]'
|
|
'| group by: id, string_col, year, month'
|
|
'|'
|
|
'08:EXCHANGE [PARTITION=UNPARTITIONED]'
|
|
'|'
|
|
'|--10:MERGE'
|
|
'| |'
|
|
'| 04:SCAN HDFS [functional.alltypes]'
|
|
'| partitions=24/24 size=956.90KB'
|
|
'|'
|
|
'09:MERGE'
|
|
'|'
|
|
'03:HASH JOIN [LEFT SEMI JOIN, PARTITIONED]'
|
|
'| hash predicates: a.id = b.id'
|
|
'|'
|
|
'|--07:EXCHANGE [PARTITION=HASH(b.id)]'
|
|
'| |'
|
|
'| 02:SCAN HDFS [functional.alltypesagg b]'
|
|
'| partitions=10/10 size=743.67KB'
|
|
'|'
|
|
'06:EXCHANGE [PARTITION=HASH(a.id)]'
|
|
'|'
|
|
'01:SCAN HDFS [functional.alltypes a]'
|
|
' partitions=1/24 size=19.71KB'
|
|
====
|
|
---- QUERY
|
|
# Tests explaining an insert query to/from an HBase table
|
|
explain insert into functional_hbase.alltypes
|
|
select a.* from functional_hbase.alltypessmall a
|
|
cross join functional.alltypessmall b
|
|
where a.year > 2009 and a.month = 4
|
|
union all
|
|
select * from functional_hbase.alltypessmall
|
|
---- RESULTS
|
|
'Estimated Per-Host Requirements: Memory=1.03GB VCores=3'
|
|
''
|
|
'WRITE TO HBASE table=functional_hbase.alltypes'
|
|
'|'
|
|
'06:EXCHANGE [PARTITION=UNPARTITIONED]'
|
|
'|'
|
|
'|--08:MERGE'
|
|
'| |'
|
|
'| 04:SCAN HBASE [functional_hbase.alltypessmall]'
|
|
'|'
|
|
'07:MERGE'
|
|
'|'
|
|
'03:CROSS JOIN [BROADCAST]'
|
|
'|'
|
|
'|--05:EXCHANGE [BROADCAST]'
|
|
'| |'
|
|
'| 02:SCAN HDFS [functional.alltypessmall b]'
|
|
'| partitions=4/4 size=6.32KB'
|
|
'|'
|
|
'01:SCAN HBASE [functional_hbase.alltypessmall a]'
|
|
' predicates: a.year > 2009, a.month = 4'
|
|
====
|