mirror of
https://github.com/apache/impala.git
synced 2025-12-30 12:02:10 -05:00
4339133887
Currently we do not support per record compression for SEQUENCEFILE; we do support no compression and block compression. Per record compression is typically very slow (since the compressor is invoked per record in the table) and not widely used. We chose to add support for per record compression as part of our effort to use Impala for all of our testdata loading infrastructure. We have per record compressed tables in testdata, so even though there is no customer demand for per record compression, we need it to migrate our data loading off of Hive. Change-Id: I6ea98ae0d31cceff8236b4b006c3a9fc00f64131 Reviewed-on: http://gerrit.sjc.cloudera.com:8080/5302 Reviewed-by: Victor Bittorf <victor.bittorf@cloudera.com> Tested-by: jenkins (cherry picked from commit f62a76f8d00b8dbc2846deb36ee5f65031ad846e) Reviewed-on: http://gerrit.sjc.cloudera.com:8080/5322
97 lines
2.2 KiB
Plaintext
97 lines
2.2 KiB
Plaintext
====
|
|
---- QUERY
|
|
drop table if exists __seq_write;
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=NONE;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
create table __seq_write (i int, s string, d double)
|
|
stored as SEQUENCEFILE;
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=NONE;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write select 0, "a", 1.1;
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=DEFAULT;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (1, "b", 2.2);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=SNAPPY;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (2, "c", 3.3);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=SNAPPY_BLOCKED;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (3, "d", 4.4);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=GZIP;
|
|
SET SEQ_COMPRESSION_MODE=BLOCK;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (4, "e", 5.5);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=NONE;
|
|
SET SEQ_COMPRESSION_MODE=RECORD;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write select 5, "a", 1.1;
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=DEFAULT;
|
|
SET SEQ_COMPRESSION_MODE=RECORD;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (6, "b", 2.2);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=SNAPPY;
|
|
SET SEQ_COMPRESSION_MODE=RECORD;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (7, "c", 3.3);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=SNAPPY_BLOCKED;
|
|
SET SEQ_COMPRESSION_MODE=RECORD;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (8, "d", 4.4);
|
|
====
|
|
---- QUERY
|
|
SET COMPRESSION_CODEC=GZIP;
|
|
SET SEQ_COMPRESSION_MODE=RECORD;
|
|
SET ALLOW_UNSUPPORTED_FORMATS=1;
|
|
insert into __seq_write values (9, "e", 5.5);
|
|
====
|
|
---- QUERY
|
|
SET ALLOW_UNSUPPORTED_FORMATS=0;
|
|
insert into __seq_write values (4, "e", 5.5);
|
|
---- CATCH
|
|
Writing to table format SEQUENCE_FILE is not supported. Use query option
|
|
====
|
|
---- QUERY
|
|
select * from __seq_write;
|
|
---- RESULTS
|
|
0,'a',1.1
|
|
1,'b',2.2
|
|
2,'c',3.3
|
|
3,'d',4.4
|
|
4,'e',5.5
|
|
5,'a',1.1
|
|
6,'b',2.2
|
|
7,'c',3.3
|
|
8,'d',4.4
|
|
9,'e',5.5
|
|
---- TYPES
|
|
INT,STRING,DOUBLE
|
|
====
|
|
---- QUERY
|
|
drop table __seq_write;
|
|
====
|