[
https://issues.apache.org/jira/browse/IMPALA-402?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16661387#comment-16661387
]
Tim Armstrong commented on IMPALA-402:
--------------------------------------
I can't reproduce this on master either with clustered or non-clustered hits.
I'm not sure which commits fixed it. I think we should add a regression test
for the gap.
{noformat}
[localhost:21000] default> create table t (i int) partitioned by (p int);
Query: create table t (i int) partitioned by (p int)
+-------------------------+
| summary |
+-------------------------+
| Table has been created. |
+-------------------------+
Fetched 1 row(s) in 0.03s
[localhost:21000] default> insert into t partition(p) /*+noclustered*/select
id, cast(rand()*10 as int) from functional.alltypestiny;
Query: insert into t partition(p) /*+noclustered*/select id, cast(rand()*10 as
int) from functional.alltypestiny
Query submitted at: 2018-10-23 15:20:38 (Coordinator:
http://tarmstrong-box:25000)
Query progress can be monitored at:
http://tarmstrong-box:25000/query_plan?query_id=3747f3c955b9784e:534d4ad300000000
Modified 8 row(s) in 0.52s
[localhost:21000] default> show partitions t;
Query: show partitions t
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
| p | #Rows | #Files | Size | Bytes Cached | Cache Replication | Format |
Incremental stats | Location |
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
| 2 | -1 | 3 | 10B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=2 |
| 3 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=3 |
| 6 | -1 | 2 | 4B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=6 |
| Total | -1 | 6 | 16B | 0B | | |
| |
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
Fetched 4 row(s) in 0.00s
{noformat}
{noformat}
[localhost:21000] default> truncate t;
Query: truncate t
Query submitted at: 2018-10-23 15:21:02 (Coordinator:
http://tarmstrong-box:25000)
Query progress can be monitored at:
http://tarmstrong-box:25000/query_plan?query_id=3342013d0b1a6fd7:1b052c9f00000000
+---------------------------+
| summary |
+---------------------------+
| Table has been truncated. |
+---------------------------+
Fetched 1 row(s) in 0.06s
[localhost:21000] default> insert into t partition(p) /*+clustered*/select id,
cast(rand()*10 as int) from functional.alltypestiny;
Query: insert into t partition(p) /*+clustered*/select id, cast(rand()*10 as
int) from functional.alltypestiny
Query submitted at: 2018-10-23 15:21:08 (Coordinator:
http://tarmstrong-box:25000)
Query progress can be monitored at:
http://tarmstrong-box:25000/query_plan?query_id=f2446f5739e65fbc:ee638d2100000000
Modified 8 row(s) in 0.41s
[localhost:21000] default> show partitions t;
Query: show partitions t
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
| p | #Rows | #Files | Size | Bytes Cached | Cache Replication | Format |
Incremental stats | Location |
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
| 0 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=0 |
| 2 | -1 | 1 | 6B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=2 |
| 3 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=3 |
| 4 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=4 |
| 6 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=6 |
| 7 | -1 | 1 | 2B | NOT CACHED | NOT CACHED | TEXT |
false | hdfs://localhost:20500/test-warehouse/t/p=7 |
| Total | -1 | 6 | 16B | 0B | | |
| |
+-------+-------+--------+------+--------------+-------------------+--------+-------------------+---------------------------------------------+
Fetched 7 row(s) in 0.01s
{noformat}
> Add test for dynamic partition expr involving rand()
> ----------------------------------------------------
>
> Key: IMPALA-402
> URL: https://issues.apache.org/jira/browse/IMPALA-402
> Project: IMPALA
> Issue Type: Improvement
> Components: Infrastructure
> Affects Versions: Impala 1.0, Impala 2.5.0, Impala 2.6.0, Impala 2.7.0,
> Impala 2.8.0, Impala 2.9.0
> Environment: CentOS 6.3
> Reporter: Benyi Wang
> Priority: Major
>
> I found two problems:
> * "Insert overwrite table" doesn't clean up the directory (external table)
> {code}
> $ hadoop fs -ls -R /user/benyiw/tmp_abc;
> drwxr-xr-x - impala supergroup 0 2013-06-06 12:46
> /user/benyiw/tmp_abc/slot=1
> -rw-r--r-- 2 impala supergroup 16088 2013-06-06 12:46
> /user/benyiw/tmp_abc/slot=1/3456606565886086588--5331466032849119435_641430213_data.0
> -rw-r--r-- 2 impala supergroup 100691 2013-06-06 12:46
> /user/benyiw/tmp_abc/slot=1/3456606565886086588--5331466032849119436_1260163059_data.0
> -rw-r--r-- 2 impala supergroup 43875 2013-06-06 12:46
> /user/benyiw/tmp_abc/slot=1/3456606565886086588--5331466032849119437_929705780_data.0
> drwxr-xr-x - impala supergroup 0 2013-06-06 12:40
> /user/benyiw/tmp_abc/slot=2
> -rw-r--r-- 2 impala supergroup 8 2013-06-06 12:40
> /user/benyiw/tmp_abc/slot=2/-8660787917599456385--5527614477985301990_1328141055_data.0
> drwxr-xr-x - impala supergroup 0 2013-06-06 12:40
> /user/benyiw/tmp_abc/slot=3
> -rw-r--r-- 2 impala supergroup 8 2013-06-06 12:40
> /user/benyiw/tmp_abc/slot=3/-8660787917599456385--5527614477985301990_501684742_data.0
> drwxr-xr-x - impala supergroup 0 2013-06-06 12:47
> /user/benyiw/tmp_abc/slot=b
> -rw-r--r-- 2 impala supergroup 16130 2013-06-06 12:47
> /user/benyiw/tmp_abc/slot=b/705210285518833776--6520969021873146409_792816606_data.0
> -rw-r--r-- 2 impala supergroup 100728 2013-06-06 12:47
> /user/benyiw/tmp_abc/slot=b/705210285518833776--6520969021873146410_157404218_data.0
> -rw-r--r-- 2 impala supergroup 43796 2013-06-06 12:47
> /user/benyiw/tmp_abc/slot=b/705210285518833776--6520969021873146411_157404218_data.0
> {code}
> * When I ran the following queries, all output files are put into the same
> partition.
> {code}
> create table tmp_abc (
> customer_id string,
> email string
> ) partitioned by (slot string)
> row format delimited fields terminated by '\t' lines terminated by '\n'
> stored as TextFile
> location '/user/benyiw/tmp_abc';
> insert overwrite table tmp_abc partition (slot) select customer_id, email,
> case when slot1 < 0.10 then "a" when slot1 < 0.70 then "b" else "c" end as
> slot from ( select customer_id, email, rand() as slot1 from (select
> customer_id, max(email) as email, sum(case when seg_num >= 0 then 1 else 0
> end) as included from customers where ( (seg_num in (1) and member = 'Y') or
> (seg_num = -1) ) and site_key = 'a_site' and coll_def_id = 'everything' group
> by customer_id having included > 0 ) a ) b
> {code}
> {code}
> $ hadoop fs -ls -R /user/benyiw/tmp_abc;
> drwxr-xr-x - impala supergroup 0 2013-06-06 13:01
> /user/benyiw/tmp_abc/slot=a
> -rw-r--r-- 2 impala supergroup 16021 2013-06-06 13:01
> /user/benyiw/tmp_abc/slot=a/-7883266034308591983--7883771993317985492_909811936_data.0
> -rw-r--r-- 2 impala supergroup 100713 2013-06-06 13:01
> /user/benyiw/tmp_abc/slot=a/-7883266034308591983--7883771993317985493_272258764_data.0
> -rw-r--r-- 2 impala supergroup 43920 2013-06-06 13:01
> /user/benyiw/tmp_abc/slot=a/-7883266034308591983--7883771993317985494_272258764_data.0
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
