Manish Maheshwari created IMPALA-11255:
------------------------------------------
Summary: Iceberg partitioned insert Error: can't multiply sequence
by non-int of type 'float'
Key: IMPALA-11255
URL: https://issues.apache.org/jira/browse/IMPALA-11255
Project: IMPALA
Issue Type: Bug
Reporter: Manish Maheshwari
Table Structures -
{code:java}
CREATE EXTERNAL TABLE prescribing_p_e.prescriptions_fact_all (
sha STRING,
pct STRING,
practice_code STRING,
bnf_presentation_code STRING,
bnf_name STRING,
items BIGINT,
nic DOUBLE,
act_cost DOUBLE,
quantity BIGINT,
period BIGINT,
not_used STRING,
no_of_records BIGINT
)
STORED AS PARQUET
LOCATION
's3a://demo-aws-go02/go02-demo/jeffrothwell/prescribing/source_parquet/prescriptions_fact_all_p'
TBLPROPERTIES ('OBJCAPABILITIES'='EXTREAD,EXTWRITE', 'STATS_GENERATED'='TASK',
'impala.events.catalogServiceId'='306320071c374e8d:9654c2f8a901e9dc',
'impala.events.catalogVersion'='78',
'impala.lastComputeStatsTime'='1641378211', 'numFiles'='51',
'numFilesErasureCoded'='0', 'numRows'='1010750195',
'spark.sql.create.version'='2.2 or prior',
'spark.sql.sources.schema.numParts'='1',
'spark.sql.sources.schema.part.0'='{\"type\":\"struct\",\"fields\":[{\"name\":\"sha\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"pct\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"practice_code\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"bnf_presentation_code\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"bnf_name\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"items\",\"type\":\"long\",\"nullable\":true,\"metadata\":{}},{\"name\":\"nic\",\"type\":\"double\",\"nullable\":true,\"metadata\":{}},{\"name\":\"act_cost\",\"type\":\"double\",\"nullable\":true,\"metadata\":{}},{\"name\":\"quantity\",\"type\":\"long\",\"nullable\":true,\"metadata\":{}},{\"name\":\"period\",\"type\":\"long\",\"nullable\":true,\"metadata\":{}},{\"name\":\"not_used\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"no_of_records\",\"type\":\"long\",\"nullable\":true,\"metadata\":{}}]}',
'totalSize'='11691280544')
CREATE EXTERNAL TABLE nhs_iceberg.prescriptions_fact_all (
sha STRING NULL,
pct STRING NULL,
practice_code STRING NULL,
bnf_presentation_code STRING NULL,
bnf_name STRING NULL,
items BIGINT NULL,
nic DOUBLE NULL,
act_cost DOUBLE NULL,
quantity BIGINT NULL,
period BIGINT NULL,
not_used STRING NULL,
no_of_records BIGINT NULL
)
PARTITIONED BY SPEC
(
period
)
STORED AS ICEBERG
LOCATION
's3a://demo-aws-go02/warehouse/tablespace/external/hive/nhs_iceberg.db/prescriptions_fact_all'
TBLPROPERTIES ('OBJCAPABILITIES'='EXTREAD,EXTWRITE',
'engine.hive.enabled'='true', 'external.table.purge'='TRUE', 'numFiles'='101',
'numFilesErasureCoded'='0', 'numRows'='1010750195',
'previous_metadata_location'='s3a://demo-aws-go02/warehouse/tablespace/external/hive/nhs_iceberg.db/prescriptions_fact_all/metadata/00002-eb138cc6-71af-491a-b3b5-d493e318d04b.metadata.json',
'table_type'='ICEBERG', 'totalSize'='15568278228',
'write.format.default'='parquet'){code}
Steps to repro the issue
{code}
create table nhs_iceberg.prescriptions_fact_all stored as iceberg as
select * from prescribing_p_e.prescriptions_fact_all where 1=2;
ALTER TABLE prescriptions_fact_all SET PARTITION SPEC (period);
insert into prescriptions_fact_all PARTITION(period)
select * from prescribing_p_e.prescriptions_fact_all ;
{code}
Result with Impala Shell
{code}
[coordinator-default-impala.dw-go02-demo-aws.ylcu-atmi.cloudera.site:443]
nhs_iceberg> create table nhs_iceberg.prescriptions_fact_all stored as iceberg
as
select * from prescribing_p_e.prescriptions_fact_all where 1=2;
Query: create table nhs_iceberg.prescriptions_fact_all stored as iceberg as
select * from prescribing_p_e.prescriptions_fact_all where 1=2
Query submitted at: 2022-04-20 23:26:34 (Coordinator:
http://coordinator-0:25000)
Query progress can be monitored at:
http://coordinator-0:25000/query_plan?query_id=874a024652fd76f1:6b70371400000000
+-------------------+
| summary |
+-------------------+
| Inserted 0 row(s) |
+-------------------+
Fetched 1 row(s) in 6.15s
[coordinator-default-impala.dw-go02-demo-aws.ylcu-atmi.cloudera.site:443]
nhs_iceberg> ALTER TABLE prescriptions_fact_all SET PARTITION SPEC (period);
Query: ALTER TABLE prescriptions_fact_all SET PARTITION SPEC (period)
+-------------------------+
| summary |
+-------------------------+
| Updated partition spec. |
+-------------------------+
Fetched 1 row(s) in 6.13s
[coordinator-default-impala.dw-go02-demo-aws.ylcu-atmi.cloudera.site:443]
nhs_iceberg> insert into prescriptions_fact_all PARTITION(period)
> select * from prescribing_p_e.prescriptions_fact_all ;
Query: insert into prescriptions_fact_all PARTITION(period)
select * from prescribing_p_e.prescriptions_fact_all
Query submitted at: 2022-04-20 23:26:53 (Coordinator:
http://coordinator-0:25000)
Query progress can be monitored at:
http://coordinator-0:25000/query_plan?query_id=23499cf597f2e719:a0cb677900000000
[Not connected] >
Unknown Exception : can't multiply sequence by non-int of type 'float'
Traceback (most recent call last):
[Not connected] > File
"/Users/manishmaheshwari/.virtualenvs/impala-shell3/lib/python3.7/site-packages/impala_shell/impala_shell.py",
line 1249, in _execute_stmt
self._periodic_wait_callback)
File
"/Users/manishmaheshwari/.virtualenvs/impala-shell3/lib/python3.7/site-packages/impala_shell/impala_client.py",
line 270, in wait_to_finish
if periodic_callback is not None: periodic_callback()
File
"/Users/manishmaheshwari/.virtualenvs/impala-shell3/lib/python3.7/site-packages/impala_shell/impala_shell.py",
line 1199, in _periodic_wait_callback
fragment_text = "[%s%s] %s%%
" % ("#" * val, " " * (100 - val), val)
TypeError: can't multiply sequence by non-int of type 'float'
[Not connected] >
[Not connected] >
{code}
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
