[BUG] [Crash Bug] SELECT * FROM <table> WHERE <condition> brings Crash #1342
Description
What happened:
SELECT * FROM <table> WHERE <condition> brings crash, when using CPU execution.
What you expected to happen:
It will not bring crash, when using CPU execution.
Minimal Complete Verifiable Example:
Query by JDBC:
CREATE TABLE t0_testtable WITH ( location = '/tmp/t0.csv', format = 'csv', persist = True, gpu = FALSE );
CREATE TABLE t0_testtable_gpu WITH ( location = '/tmp/t0.csv', format = 'csv', persist = True, gpu = TRUE );
SELECT * FROM t0 WHERE (NOT t0.c0);t0.csv:
c0,
'false',
SQL:
SELECT * FROM t0 WHERE (NOT t0.c0);Result:
Query is gone (server restarted?)Due to a crash caused by this query, the Dask-sql server restarted.
SQL:
SELECT * FROM t0_gpu WHERE (NOT t0_gpu.c0);Result:
c0 | Unnamed: 1
----+------------
(0 rows)Query by python:
import dask.dataframe as dd
from dask_sql import Context
import pandas as pd
c = Context()
df0 = pd.DataFrame({
'c0':['false'],
})
t0 = dd.from_pandas(df0, npartitions=1)
c.create_table('t0', t0, persist = True, gpu=False)
c.create_table('t0_gpu', t0, persist = True, gpu=True)
print('GPU Result:')
result2= c.sql("SELECT * FROM t0_gpu WHERE (NOT t0_gpu.c0)").compute()
print(result2)
print('CPU Result:')
result1= c.sql("SELECT * FROM t0 WHERE (NOT t0.c0)").compute()
print(result1)Result:
INFO:numba.cuda.cudadrv.driver:init
GPU Result:
Empty DataFrame
Columns: [c0]
Index: []
CPU Result:
Traceback (most recent call last):
File "/tmp/test.py", line 19, in <module>
result1= c.sql("SELECT * FROM t0 WHERE (NOT t0.c0)").compute()
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/base.py", line 314, in compute
(result,) = compute(self, traverse=False, **kwargs)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/base.py", line 599, in compute
results = schedule(dsk, keys, **kwargs)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/threaded.py", line 89, in get
results = get_async(
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/local.py", line 511, in get_async
raise_exception(exc, tb)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/local.py", line 319, in reraise
raise exc
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/local.py", line 224, in execute_task
result = _execute_task(task, data)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/optimization.py", line 990, in __call__
return core.get(self.dsk, self.outkey, dict(zip(self.inkeys, args)))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 149, in get
result = _execute_task(task, cache)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 113, in _execute_task
return [_execute_task(a, cache) for a in arg]
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 113, in <listcomp>
return [_execute_task(a, cache) for a in arg]
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in <genexpr>
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/utils.py", line 73, in apply
return func(*args, **kwargs)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/dask/utils.py", line 1105, in __call__
return getattr(__obj, self.method)(*args, **kwargs)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/generic.py", line 6240, in astype
new_data = self._mgr.astype(dtype=dtype, copy=copy, errors=errors)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/internals/managers.py", line 448, in astype
return self.apply("astype", dtype=dtype, copy=copy, errors=errors)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/internals/managers.py", line 352, in apply
applied = getattr(b, f)(**kwargs)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/internals/blocks.py", line 526, in astype
new_values = astype_array_safe(values, dtype, copy=copy, errors=errors)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/dtypes/astype.py", line 299, in astype_array_safe
new_values = astype_array(values, dtype, copy=copy)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/dtypes/astype.py", line 230, in astype_array
values = astype_nansafe(values, dtype, copy=copy)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/dtypes/astype.py", line 95, in astype_nansafe
return dtype.construct_array_type()._from_sequence(arr, dtype=dtype, copy=copy)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/arrays/masked.py", line 132, in _from_sequence
values, mask = cls._coerce_to_array(scalars, dtype=dtype, copy=copy)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/arrays/boolean.py", line 344, in _coerce_to_array
return coerce_to_array(value, copy=copy)
File "/opt/conda/envs/rapids/lib/python3.10/site-packages/pandas/core/arrays/boolean.py", line 194, in coerce_to_array
raise TypeError("Need to pass bool-like values")
TypeError: Need to pass bool-like values
Anything else we need to know?:
Environment:
- dask-sql version: 2023.6.0
- Python version: Python 3.10.11
- Operating System: Ubuntu22.04
- Install method (conda, pip, source): Docker deploy by https://hub.docker.com/layers/rapidsai/rapidsai-dev/23.06-cuda11.8-devel-ubuntu22.04-py3.10/images/sha256-cfbb61fdf7227b090a435a2e758114f3f1c31872ed8dbd96e5e564bb5fd184a7?context=explore