[
https://issues.apache.org/jira/browse/DRILL-1153?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14072143#comment-14072143
]
Chun Chang commented on DRILL-1153:
-----------------------------------
0: jdbc:drill:schema=dfs> explain plan for select time_by_day.the_year as c0,
sum(sales_fact_1997.unit_sales) as m0, count(distinct
sales_fact_1997.customer_id) as m1 from time_by_day as time_by_day,
sales_fact_1997 as sales_fact_1997 where sales_fact_1997.time_id =
time_by_day.time_id and time_by_day.the_year = 1997 group by
time_by_day.the_year;
+------------+------------+
| text | json |
+------------+------------+
| 00-00 Screen
00-01 Project(c0=[$0], m0=[$1], m1=[$2])
00-02 Project(c0=[$0], m0=[CASE(=($2, 0), null, $1)], m1=[$4])
00-03 HashJoin(condition=[IS NOT DISTINCT FROM($0, $3)],
joinType=[inner])
00-05 HashAgg(group=[{0}], agg#0=[$SUM0($1)], agg#1=[COUNT($1)])
00-07 Project(c0=[$0], unit_sales=[$3], customer_id=[$4])
00-09 HashJoin(condition=[=($2, $1)], joinType=[inner])
00-12 SelectionVectorRemover
00-15 Filter(condition=[=(CAST($0):INTEGER, 1997)])
00-19 Project(the_year=[$1], time_id=[$0])
00-23 ProducerConsumer
00-26 Scan(groupscan=[ParquetGroupScan
[entries=[ReadEntryWithPath [path=maprfs:/user/root/mondrian/time_by_day]],
selectionRoot=/user/root/mondrian/time_by_day, columns=[SchemaPath
[`the_year`], SchemaPath [`time_id`]]]])
00-11 Project(time_id0=[$0], unit_sales=[$1], customer_id=[$2])
00-14 Project(time_id=[$2], unit_sales=[$0],
customer_id=[$1])
00-18 ProducerConsumer
00-22 Scan(groupscan=[ParquetGroupScan
[entries=[ReadEntryWithPath [path=maprfs:/user/root/mondrian/sales_fact_1997]],
selectionRoot=/user/root/mondrian/sales_fact_1997, columns=[SchemaPath
[`time_id`], SchemaPath [`unit_sales`], SchemaPath [`customer_id`]]]])
00-04 Project(c00=[$0], m1=[$1])
00-06 HashAgg(group=[{0}], m1=[COUNT($1)])
00-08 HashAgg(group=[{0, 1}])
00-10 Project(c0=[$0], customer_id=[$3])
00-13 HashJoin(condition=[=($2, $1)], joinType=[inner])
00-17 SelectionVectorRemover
00-21 Filter(condition=[=(CAST($0):INTEGER, 1997)])
00-25 Project(the_year=[$1], time_id=[$0])
00-28 ProducerConsumer
00-29 Scan(groupscan=[ParquetGroupScan
[entries=[ReadEntryWithPath [path=maprfs:/user/root/mondrian/time_by_day]],
selectionRoot=/user/root/mondrian/time_by_day, columns=[SchemaPath
[`the_year`], SchemaPath [`time_id`]]]])
00-16 Project(time_id0=[$0], customer_id=[$1])
00-20 Project(time_id=[$1], customer_id=[$0])
00-24 ProducerConsumer
00-27 Scan(groupscan=[ParquetGroupScan
[entries=[ReadEntryWithPath [path=maprfs:/user/root/mondrian/sales_fact_1997]],
selectionRoot=/user/root/mondrian/sales_fact_1997, columns=[SchemaPath
[`time_id`], SchemaPath [`customer_id`]]]])
| {
"head" : {
"version" : 1,
"generator" : {
"type" : "ExplainHandler",
"info" : ""
},
"type" : "APACHE_DRILL_PHYSICAL",
"options" : [ ],
"queue" : 0,
"resultMode" : "EXEC"
},
"graph" : [ {
"pop" : "parquet-scan",
"@id" : 26,
"entries" : [ {
"path" : "maprfs:/user/root/mondrian/time_by_day"
} ],
"storage" : {
"type" : "file",
"enabled" : true,
"connection" : "maprfs:///",
"workspaces" : {
"default" : {
"location" : "/user/root/mondrian/",
"writable" : false,
"storageformat" : null
},
"home" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"root" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"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" : [ "`the_year`", "`time_id`" ],
"selectionRoot" : "/user/root/mondrian/time_by_day",
"cost" : 730.0
}, {
"pop" : "producer-consumer",
"@id" : 23,
"child" : 26,
"size" : 10,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 730.0
}, {
"pop" : "project",
"@id" : 19,
"exprs" : [ {
"ref" : "`the_year`",
"expr" : "`the_year`"
}, {
"ref" : "`time_id`",
"expr" : "`time_id`"
} ],
"child" : 23,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 730.0
}, {
"pop" : "filter",
"@id" : 15,
"child" : 19,
"expr" : "equal(cast( (`the_year` ) as INT ), 1997) ",
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 109.5
}, {
"pop" : "selection-vector-remover",
"@id" : 12,
"child" : 15,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 109.5
}, {
"pop" : "parquet-scan",
"@id" : 22,
"entries" : [ {
"path" : "maprfs:/user/root/mondrian/sales_fact_1997"
} ],
"storage" : {
"type" : "file",
"enabled" : true,
"connection" : "maprfs:///",
"workspaces" : {
"default" : {
"location" : "/user/root/mondrian/",
"writable" : false,
"storageformat" : null
},
"home" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"root" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"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" : [ "`time_id`", "`unit_sales`", "`customer_id`" ],
"selectionRoot" : "/user/root/mondrian/sales_fact_1997",
"cost" : 86837.0
}, {
"pop" : "producer-consumer",
"@id" : 18,
"child" : 22,
"size" : 10,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 86837.0
}, {
"pop" : "project",
"@id" : 14,
"exprs" : [ {
"ref" : "`time_id`",
"expr" : "`time_id`"
}, {
"ref" : "`unit_sales`",
"expr" : "`unit_sales`"
}, {
"ref" : "`customer_id`",
"expr" : "`customer_id`"
} ],
"child" : 18,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 86837.0
}, {
"pop" : "project",
"@id" : 11,
"exprs" : [ {
"ref" : "`time_id0`",
"expr" : "`time_id`"
}, {
"ref" : "`unit_sales`",
"expr" : "`unit_sales`"
}, {
"ref" : "`customer_id`",
"expr" : "`customer_id`"
} ],
"child" : 14,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 86837.0
}, {
"pop" : "hash-join",
"@id" : 9,
"left" : 12,
"right" : 11,
"conditions" : [ {
"relationship" : "==",
"left" : "`time_id`",
"right" : "`time_id0`"
} ],
"joinType" : "INNER",
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 0.0
}, {
"pop" : "project",
"@id" : 7,
"exprs" : [ {
"ref" : "`c0`",
"expr" : "`the_year`"
}, {
"ref" : "`unit_sales`",
"expr" : "`unit_sales`"
}, {
"ref" : "`customer_id`",
"expr" : "`customer_id`"
} ],
"child" : 9,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 1.0
}, {
"pop" : "hash-aggregate",
"@id" : 5,
"child" : 7,
"cardinality" : 1.0,
"initialAllocation" : 1000000,
"maxAllocation" : 10000000000,
"cost" : 0.5,
"groupByExprs" : [ {
"ref" : "`c0`",
"expr" : "`c0`"
} ],
"aggrExprs" : [ {
"ref" : "`$f1`",
"expr" : "$sum0(`unit_sales`) "
}, {
"ref" : "`$f2`",
"expr" : "count(`unit_sales`) "
} ]
}, {
"pop" : "parquet-scan",
"@id" : 27,
"entries" : [ {
"path" : "maprfs:/user/root/mondrian/sales_fact_1997"
} ],
"storage" : {
"type" : "file",
"enabled" : true,
"connection" : "maprfs:///",
"workspaces" : {
"default" : {
"location" : "/user/root/mondrian/",
"writable" : false,
"storageformat" : null
},
"home" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"root" : {
"location" : "/",
"writable" : false,
"storageformat" : null
},
"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"
}
}
},
"forma |
+------------+------------+
1 row selected (6.62 seconds)
> Missing Function: $sum0(FLOAT8-OPTIONAL)
> ----------------------------------------
>
> Key: DRILL-1153
> URL: https://issues.apache.org/jira/browse/DRILL-1153
> Project: Apache Drill
> Issue Type: Bug
> Components: Functions - Drill
> Reporter: Chun Chang
> Assignee: Chun Chang
> Fix For: 1.0.0-BETA1
>
>
> #Mon Jul 14 10:10:52 PDT 2014
> git.commit.id.abbrev=699851b
> The following mondrian query (query106.q) failed due to schema change
> exception:
> 0: jdbc:drill:schema=dfs> select time_by_day.the_year as c0,
> sum(sales_fact_1997.unit_sales) as m0, count(distinct
> sales_fact_1997.customer_id) as m1 from time_by_day as time_by_day,
> sales_fact_1997 as sales_fact_1997 where sales_fact_1997.time_id =
> time_by_day.time_id and time_by_day.the_year = 1997 group by
> time_by_day.the_year;
> Query failed: org.apache.drill.exec.rpc.RpcException: Remote failure while
> running query.[error_id: "d7d30240-1688-4db2-a703-e9a0a52a19e2"
> endpoint {
> address: "qa-node117.qa.lab"
> user_port: 31010
> control_port: 31011
> data_port: 31012
> }
> error_type: 0
> message: "Failure while running fragment. < IllegalStateException:[ You tried
> to do a batch data read operation when you were in a state of STOP. You can
> only do this type of operation when you are in a state of OK or
> OK_NEW_SCHEMA. ]"
> ]
> Error: exception while executing query (state=,code=0)
--
This message was sent by Atlassian JIRA
(v6.2#6252)
