[
https://issues.apache.org/jira/browse/DRILL-774?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14002168#comment-14002168
]
Zhiyong Liu commented on DRILL-774:
-----------------------------------
Here you go:
0: jdbc:drill:schema=dfs.TpcHMulti> explain plan for select l.l_partkey,
count(*) from lineitem l, partsupp ps where l.l_partkey = ps.ps_partkey group
by l.l_partkey;
+------------+------------+
| text | json |
+------------+------------+
| ScreenPrel
UnionExchangePrel
HashAggPrel(group=[{0}], EXPR$1=[COUNT()])
ProjectPrel(l_partkey=[$1])
HashJoinPrel(condition=[=($1, $3)], joinType=[inner])
HashToRandomExchangePrel(dist0=[[$1]])
ScanPrel(groupscan=[ParquetGroupScan [entries=[ReadEntryWithPath
[path=maprfs:/drill/testdata/tpch-multi/lineitem]],
selectionRoot=/drill/testdata/tpch-multi/lineitem, columns=[SchemaPath
[`l_partkey`]]]])
HashToRandomExchangePrel(dist0=[[$1]])
ScanPrel(groupscan=[ParquetGroupScan [entries=[ReadEntryWithPath
[path=maprfs:/drill/testdata/tpch-multi/partsupp]],
selectionRoot=/drill/testdata/tpch-multi/partsupp, columns=[SchemaPath
[`ps_partkey`]]]])
| {
"head" : {
"version" : 1,
"generator" : {
"type" : "ExplainHandler",
"info" : ""
},
"type" : "APACHE_DRILL_PHYSICAL",
"options" : [ ],
"resultMode" : "EXEC"
},
"graph" : [ {
"pop" : "parquet-scan",
"@id" : 1,
"entries" : [ {
"path" : "maprfs:/drill/testdata/tpch-multi/lineitem"
} ],
"storage" : {
"type" : "file",
"connection" : "maprfs:///",
"workspaces" : {
"root" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"TpcHMulti" : {
"location" : "/drill/testdata/tpch-multi",
"writable" : true,
"storageformat" : "parquet"
},
"TpcH001" : {
"location" : "/drill/testdata/tpch001",
"writable" : true,
"storageformat" : "parquet"
},
"P1Tests" : {
"location" : "/drill/testdata/p1tests",
"writable" : true,
"storageformat" : "parquet"
},
"Krystal" : {
"location" : "/drill/testdata/krystal",
"writable" : true,
"storageformat" : "parquet"
},
"Amplab" : {
"location" : "/drill/testdata/amplab",
"writable" : true,
"storageformat" : "parquet"
},
"tmp" : {
"location" : "/tmp",
"writable" : true,
"storageformat" : "csv"
}
},
"formats" : {
"psv" : {
"type" : "text",
"extensions" : [ "tbl" ],
"delimiter" : "|"
},
"csv" : {
"type" : "text",
"extensions" : [ "csv" ],
"delimiter" : ","
},
"tsv" : {
"type" : "text",
"extensions" : [ "tsv" ],
"delimiter" : "\t"
},
"parquet" : {
"type" : "parquet"
},
"json" : {
"type" : "json"
}
}
},
"format" : {
"type" : "parquet"
},
"columns" : [ "`l_partkey`" ],
"selectionRoot" : "/drill/testdata/tpch-multi/lineitem"
}, {
"pop" : "hash-to-random-exchange",
"@id" : 2,
"child" : 1,
"expr" : "hash(`l_partkey`) ",
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "parquet-scan",
"@id" : 3,
"entries" : [ {
"path" : "maprfs:/drill/testdata/tpch-multi/partsupp"
} ],
"storage" : {
"type" : "file",
"connection" : "maprfs:///",
"workspaces" : {
"root" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"TpcHMulti" : {
"location" : "/drill/testdata/tpch-multi",
"writable" : true,
"storageformat" : "parquet"
},
"TpcH001" : {
"location" : "/drill/testdata/tpch001",
"writable" : true,
"storageformat" : "parquet"
},
"P1Tests" : {
"location" : "/drill/testdata/p1tests",
"writable" : true,
"storageformat" : "parquet"
},
"Krystal" : {
"location" : "/drill/testdata/krystal",
"writable" : true,
"storageformat" : "parquet"
},
"Amplab" : {
"location" : "/drill/testdata/amplab",
"writable" : true,
"storageformat" : "parquet"
},
"tmp" : {
"location" : "/tmp",
"writable" : true,
"storageformat" : "csv"
}
},
"formats" : {
"psv" : {
"type" : "text",
"extensions" : [ "tbl" ],
"delimiter" : "|"
},
"csv" : {
"type" : "text",
"extensions" : [ "csv" ],
"delimiter" : ","
},
"tsv" : {
"type" : "text",
"extensions" : [ "tsv" ],
"delimiter" : "\t"
},
"parquet" : {
"type" : "parquet"
},
"json" : {
"type" : "json"
}
}
},
"format" : {
"type" : "parquet"
},
"columns" : [ "`ps_partkey`" ],
"selectionRoot" : "/drill/testdata/tpch-multi/partsupp"
}, {
"pop" : "hash-to-random-exchange",
"@id" : 4,
"child" : 3,
"expr" : "hash(`ps_partkey`) ",
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "project",
"@id" : 5,
"exprs" : [ {
"ref" : "`*0`",
"expr" : "`*`"
}, {
"ref" : "`ps_partkey`",
"expr" : "`ps_partkey`"
} ],
"child" : 4,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "hash-join",
"@id" : 6,
"left" : 2,
"right" : 5,
"conditions" : [ {
"relationship" : "==",
"left" : "`l_partkey`",
"right" : "`ps_partkey`"
} ],
"joinType" : "INNER",
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "project",
"@id" : 7,
"exprs" : [ {
"ref" : "`l_partkey`",
"expr" : "`l_partkey`"
} ],
"child" : 6,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "hash-aggregate",
"@id" : 8,
"child" : 7,
"cardinality" : 1.0,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"groupByExprs" : [ {
"ref" : "`l_partkey`",
"expr" : "`l_partkey`"
} ],
"aggrExprs" : [ {
"ref" : "`EXPR$1`",
"expr" : "count(1) "
} ],
"htConfig" : {
"initialCapacity" : 256,
"loadFactor" : 0.75,
"keyExprsBuild" : [ {
"ref" : "`l_partkey`",
"expr" : "`l_partkey`"
} ],
"keyExprsProbe" : null
}
}, {
"pop" : "union-exchange",
"@id" : 9,
"child" : 8,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
}, {
"pop" : "screen",
"@id" : 10,
"child" : 9,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000
} ]
} |
+------------+------------+
1 row selected (0.118 seconds)
> verification fails for group-by
> -------------------------------
>
> Key: DRILL-774
> URL: https://issues.apache.org/jira/browse/DRILL-774
> Project: Apache Drill
> Issue Type: Bug
> Components: Functions - Drill
> Reporter: Zhiyong Liu
>
> Datasources: TPCH (10MB), three-way split parquet files
> git.commit.id.abbrev=70fab8c
> git.commit.id=70fab8c968a6dc05471aa1f32009cd15945d4f3d
> Verification fails for the following query:
> 2014-05-19 10:39:34 INFO QuerySubmitter:92 - Submitting query:
>
> select l.l_partkey, count(*)
>
> from lineitem l,
>
> partsupp ps
>
> where l.l_partkey = ps.ps_partkey
>
> group by l.l_partkey
>
> 2014-05-19 10:39:35 INFO DrillTestBase:198 - Query submit end time:
> 2014/05/19 10:39:35.0035
> 2014-05-19 10:39:35 INFO DrillTestBase:199 - The execution time for the
> query: 1 seconds.
> 2014-05-19 10:39:35 INFO TestVerifier:203 - These rows are not expected:
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 1245 11 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 1296 63 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 929 103 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 1245 117 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 1125 105 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 929 1 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:206 - 1251 96 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:213 - Total number of unexpected rows:
> 7
> 2014-05-19 10:39:35 INFO TestVerifier:217 - These rows are expected but are
> not in result set:
> 2014-05-19 10:39:35 INFO TestVerifier:220 - 1125 140 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:220 - 929 104 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:220 - 1296 84 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:220 - 1245 128 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:220 - 1251 128 : 1 time(s).
>
> 2014-05-19 10:39:35 INFO TestVerifier:227 - Total number of expected but
> missing: 5
--
This message was sent by Atlassian JIRA
(v6.2#6252)
