Quanlong Huang created IMPALA-12796:
---------------------------------------
Summary: Several tests in test_scanners.py failed by wrong row
counts
Key: IMPALA-12796
URL: https://issues.apache.org/jira/browse/IMPALA-12796
Project: IMPALA
Issue Type: Bug
Reporter: Quanlong Huang
Assignee: Riza Suminto
Several tests in test_scanners.py failed by wrong row counts. The actual row
count is extremely large, e.g
{noformat}
query_test/test_scanners.py:97: in test_scanners
self.run_test_case('QueryTest/scanners', new_vector)
common/impala_test_suite.py:756: in run_test_case
self.__verify_results_and_errors(vector, test_section, result, use_db)
common/impala_test_suite.py:589: in __verify_results_and_errors
replace_filenames_with_placeholder)
common/test_result_verifier.py:487: in verify_raw_results
VERIFIER_MAP[verifier](expected, actual)
common/test_result_verifier.py:296: in verify_query_result_is_equal
assert expected_results == actual_results
E assert Comparing QueryTestResults (expected vs actual):
E 100 != 378250{noformat}
The query is
{code:sql}
select count(*) from alltypessmall;{code}
Console output:
{noformat}
SET
client_identifier=query_test/test_scanners.py::TestScannersAllTableFormats::()::test_scanners[protocol:beeswax|table_format:parquet/none|exec_option:{'test_replan':1;'batch_size':0;'num_nodes':0;'disable_codegen_rows_threshold':0;'disable_codegen':False;'abort_on_error':1;;
-- connecting to: localhost:21000
-- 2024-02-07 11:06:41,035 INFO MainThread: Could not connect to ('::1',
21000, 0, 0)
Traceback (most recent call last):
File
"/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/Impala-Toolchain/toolchain-packages-gcc10.4.0/thrift-0.16.0-p6/python/lib/python2.7/site-packages/thrift/transport/TSocket.py",
line 137, in open
handle.connect(sockaddr)
File
"/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/Impala-Toolchain/toolchain-packages-gcc10.4.0/python-2.7.16/lib/python2.7/socket.py",
line 228, in meth
return getattr(self._sock,name)(*args)
error: [Errno 111] Connection refused
-- connecting to localhost:21050 with impyla
-- 2024-02-07 11:06:41,035 INFO MainThread: Could not connect to ('::1',
21050, 0, 0)
Traceback (most recent call last):
File
"/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/Impala-Toolchain/toolchain-packages-gcc10.4.0/thrift-0.16.0-p6/python/lib/python2.7/site-packages/thrift/transport/TSocket.py",
line 137, in open
handle.connect(sockaddr)
File
"/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/Impala-Toolchain/toolchain-packages-gcc10.4.0/python-2.7.16/lib/python2.7/socket.py",
line 228, in meth
return getattr(self._sock,name)(*args)
error: [Errno 111] Connection refused
-- 2024-02-07 11:06:41,049 INFO MainThread: Closing active operation
-- connecting to localhost:28000 with impyla
-- 2024-02-07 11:06:41,073 INFO MainThread: Closing active operation
SET
client_identifier=query_test/test_scanners.py::TestScannersAllTableFormats::()::test_scanners[protocol:beeswax|table_format:parquet/none|exec_option:{'test_replan':1;'batch_size':0;'num_nodes':0;'disable_codegen_rows_threshold':0;'disable_codegen':False;'abort_on_error':1;;
-- executing against localhost:21000
use functional_parquet;
-- 2024-02-07 11:06:41,085 INFO MainThread: Started query
8c4dd086f2a4904d:45aea02c00000000
SET
client_identifier=query_test/test_scanners.py::TestScannersAllTableFormats::()::test_scanners[protocol:beeswax|table_format:parquet/none|exec_option:{'test_replan':1;'batch_size':0;'num_nodes':0;'disable_codegen_rows_threshold':0;'disable_codegen':False;'abort_on_error':1;;
SET test_replan=1;
SET mt_dop=1;
SET batch_size=0;
SET num_nodes=0;
SET disable_codegen_rows_threshold=0;
SET disable_codegen=False;
SET abort_on_error=1;
SET exec_single_node_rows_threshold=0;
-- 2024-02-07 11:06:41,086 INFO MainThread: Loading query test file:
/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/repos/Impala/testdata/workloads/functional-query/queries/QueryTest/scanners.test
-- executing against localhost:21000
select count(*),
sum(id), count(bool_col), sum(tinyint_col), sum(smallint_col),
sum(int_col), sum(bigint_col), max(float_col), max(double_col),
max(date_string_col), max(string_col), max(timestamp_col)
from alltypesagg
where id % 2 = 0 and day is not null;
-- 2024-02-07 11:06:43,214 INFO MainThread: Started query
fa4256b842b4ca06:d121dbbf00000000
-- executing against localhost:21000
select sum(t1.id), sum(t1.int_col),max(t1.date_string_col), max(t2.string_col)
from alltypesagg t1
inner join alltypesagg t2
on t1.id = t2.id and t1.day is not null and t2.day is not null;
-- 2024-02-07 11:06:43,805 INFO MainThread: Started query
d54c506ddf7aab85:f8a09ce600000000
-- executing against localhost:21000
select id, bool_col, int_col
from alltypesagg where day is not null
order by 1 desc, 2 desc, 3 desc
limit 10;
-- 2024-02-07 11:06:44,023 INFO MainThread: Started query
1e4c81bf3989f31f:c3b3b67000000000
-- executing against localhost:21000
select count(*)
from nulltable;
-- 2024-02-07 11:06:44,131 INFO MainThread: Started query
ba48e2f6736341e1:a21ad19300000000
-- executing against localhost:21000
select count(*)
from nulltable where b = '';
-- 2024-02-07 11:06:44,191 INFO MainThread: Started query
f6414ed0b07a6ab2:c229fef700000000
-- executing against localhost:21000
select a,b
from nulltable where b = '';
-- 2024-02-07 11:06:44,300 INFO MainThread: Started query
3d4db322071343d6:6f502d3f00000000
-- executing against localhost:21000
select count(*) from alltypes where rand() * 10 >= 0.0;
-- 2024-02-07 11:06:44,408 INFO MainThread: Started query
294652aec4885cad:0849ff0800000000
-- executing against localhost:21000
select count(*) from alltypes where rand() * 10 < 0.0;
-- 2024-02-07 11:06:44,516 INFO MainThread: Started query
7f466c573914447e:65c6ca1800000000
-- executing against localhost:21000
select count(*) from alltypes where rand() - year > month;
-- 2024-02-07 11:06:44,624 INFO MainThread: Started query
b641073231fd65d1:0f9c184200000000
-- executing against localhost:21000
select count(v.x) from alltypestiny t3 left outer join (
select true as x from alltypestiny t1 left outer join
alltypestiny t2 on (true)) v
on (v.x = t3.bool_col) where t3.bool_col = true;
-- 2024-02-07 11:06:44,737 INFO MainThread: Started query
c44facd1194ba102:48e6531a00000000
-- executing against localhost:21000
select * from emptytable;
-- 2024-02-07 11:06:44,955 INFO MainThread: Started query
404cbcb82628ae02:10b500a900000000
-- executing against localhost:21000
set max_scan_range_length=1;
-- 2024-02-07 11:06:45,010 INFO MainThread: Started query
30456d0b30ca6353:9d00b58700000000
-- executing against localhost:21000
select count(*) from alltypessmall;
-- 2024-02-07 11:06:45,014 INFO MainThread: Started query
6f47560afcee03e9:e6a9bc0f00000000
-- executing against localhost:21000
SET MAX_SCAN_RANGE_LENGTH="0";
-- 2024-02-07 11:06:45,675 INFO MainThread: Started query
da4cb660d639198e:3797933000000000
-- 2024-02-07 11:06:45,688 ERROR MainThread: Comparing QueryTestResults
(expected vs actual):
100 != 378250{noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
