jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2025-12-25 02:03:09 -05:00
Code Issues Projects Releases Wiki Activity

IMPALA-7165: [DOCS] Correct example for dynamic partition pruning

Browse Source 
Change-Id: I44d1054f55d3dc7947ccf4c2ef440e506c41f963
Reviewed-on: http://gerrit.cloudera.org:8080/10703
Reviewed-by: Vuk Ercegovac <vercegovac@cloudera.com>
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
This commit is contained in:
Alex Rodoni
2018-06-12 16:18:20 -07:00
committed by Impala Public Jenkins
parent b864112fa2
commit d29d5a25e5
3 changed files with 99 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
docs/shared/impala_common.xml
View File

@@ -1870,42 +1870,44 @@ from length_demo;
</p>
<codeblock id="simple_dpp_example">
create table yy (s string) partitioned by (year int) stored as parquet;
insert into yy partition (year) values ('1999', 1999), ('2000', 2000),
('2001', 2001), ('2010',2010);
compute stats yy;
CREATE TABLE yy (s STRING) PARTITIONED BY (year INT);
INSERT INTO yy PARTITION (year) VALUES ('1999', 1999), ('2000', 2000),
('2001', 2001), ('2010', 2010), ('2018', 2018);
COMPUTE STATS yy;
create table yy2 (s string) partitioned by (year int) stored as parquet;
insert into yy2 partition (year) values ('1999', 1999), ('2000', 2000),
('2001', 2001);
compute stats yy2;
CREATE TABLE yy2 (s STRING, year INT);
INSERT INTO yy2 VALUES ('1999', 1999), ('2000', 2000), ('2001', 2001);
COMPUTE STATS yy2;
-- The query reads an unknown number of partitions, whose key values are only
-- known at run time. The 'runtime filters' lines show how the information about
-- the partitions is calculated in query fragment 02, and then used in query
-- fragment 00 to decide which partitions to skip.
explain select s from yy2 where year in (select year from yy where year between 2000 and 2005);
+----------------------------------------------------------+
| Explain String |
+----------------------------------------------------------+
| Estimated Per-Host Requirements: Memory=16.00MB VCores=2 |
| |
| 04:EXCHANGE [UNPARTITIONED] |
| | |
| 02:HASH JOIN [LEFT SEMI JOIN, BROADCAST] |
| | hash predicates: year = year |
| | <b>runtime filters: RF000 &lt;- year</b> |
| | |
| |--03:EXCHANGE [BROADCAST] |
| | | |
| | 01:SCAN HDFS [dpp.yy] |
| | partitions=2/4 files=2 size=468B |
| | |
| 00:SCAN HDFS [dpp.yy2] |
| partitions=2/3 files=2 size=468B |
| <b>runtime filters: RF000 -> year</b> |
+----------------------------------------------------------+
-- The following query reads an unknown number of partitions, whose key values
-- are only known at run time. The 'runtime filters' lines show how the
-- information about the partitions is calculated in query fragment 02, and then
-- used in query fragment 00 to decide which partitions to skip.
EXPLAIN SELECT s FROM yy WHERE year IN (SELECT year FROM yy2);
+--------------------------------------------------------------------------+
| PLAN-ROOT SINK |
| | |
| 04:EXCHANGE [UNPARTITIONED] |
| | |
| 02:HASH JOIN [LEFT SEMI JOIN, BROADCAST] |
| | hash predicates: year = year |
| | <b>runtime filters: RF000 &lt;- year</b> |
| | |
| |--03:EXCHANGE [BROADCAST] |
| | | |
| | 01:SCAN HDFS [default.yy2] |
| | partitions=1/1 files=1 size=620B |
| | |
| 00:SCAN HDFS [default.yy] |
| <b>partitions=5/5</b> files=5 size=1.71KB |
| runtime filters: RF000 -> year |
+--------------------------------------------------------------------------+
SELECT s FROM yy WHERE year IN (SELECT year FROM yy2); -- Returns 3 rows from yy
PROFILE;
</codeblock>
<p id="order_by_scratch_dir">
By default, intermediate files used during large sort, join, aggregation, or analytic function operations
are stored in the directory <filepath>/tmp/impala-scratch</filepath> . These files are removed when the