[ASTERIXDB-1340] Index does not have a valid resource ID

• Type: Bug
• Status: Resolved
• Priority: Critical
• Resolution: Fixed
• Component/s: *DB - AsterixDB, STO - Storage
• Assignee: Murtadha Makki Al Hubail
• Reporter: Yingyi Bu
• Created: 11/Mar/16 01:38
• Updated: 12/Mar/16 19:04
• Resolved: 12/Mar/16 19:04

Description

I created a 3 NC cluster on a single machine, using the attached cluster configuration (local3.xml) and instance configuration (asterix-configuration.xml). The CSV files for the datasets are attached. Then I ran the following query.

DDL:

drop dataverse tpch if exists;
create dataverse tpch;

use dataverse tpch;

create type LineItemType as closed {
  l_orderkey: int64,
  l_partkey: int64,
  l_suppkey: int64,
  l_linenumber: int64,
  l_quantity: int64,
  l_extendedprice: double,
  l_discount: double,
  l_tax: double,
  l_returnflag: string,
  l_linestatus: string,
  l_shipdate: string,
  l_commitdate: string,
  l_receiptdate: string,
  l_shipinstruct: string,
  l_shipmode: string,
  l_comment: string
}

create type OrderType as closed {
  o_orderkey: int64,
  o_custkey: int64,
  o_orderstatus: string,
  o_totalprice: double,
  o_orderdate: string,
  o_orderpriority: string,
  o_clerk: string,
  o_shippriority: int64,
  o_comment: string
}

create dataset LineItem(LineItemType)
  primary key l_orderkey, l_linenumber;
create dataset Orders(OrderType)
  primary key o_orderkey;

DML:

use dataverse tpch;

load dataset LineItem 
using "org.apache.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="asterix_nc1:///data/lineitem.tbl"),("format"="delimited-text"),("delimiter"="|"));

load dataset Orders 
using "org.apache.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="asterix_nc1:///data/orders.tbl"),("format"="delimited-text"),("delimiter"="|"));

Query:

use dataverse tpch;

declare function tmp()
{
  for $l in dataset('LineItem')
  where $l.l_commitdate < $l.l_receiptdate
  distinct by $l.l_orderkey
  return { "o_orderkey": $l.l_orderkey }
}

for $o in dataset('Orders')
for $t in tmp()
where $o.o_orderkey = $t.o_orderkey and 
  $o.o_orderdate >= '1993-07-01' and $o.o_orderdate < '1993-10-01' 
group by $o_orderpriority := $o.o_orderpriority with $o
order by $o_orderpriority
return {
  "order_priority": $o_orderpriority,
  "count": count($o)
}

The query fails with the following exception:

org.apache.hyracks.api.exceptions.HyracksDataException: java.util.concurrent.ExecutionException: org.apache.hyracks.api.exceptions.HyracksDataException: Index does not have a valid resource ID. Has it been created yet?
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable.runInParallel(SuperActivityOperatorNodePushable.java:218)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable.initialize(SuperActivityOperatorNodePushable.java:83)
        at org.apache.hyracks.control.nc.Task.run(Task.java:261)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.ExecutionException: org.apache.hyracks.api.exceptions.HyracksDataException: Index does not have a valid resource ID. Has it been created yet?
        at java.util.concurrent.FutureTask.report(FutureTask.java:122)
        at java.util.concurrent.FutureTask.get(FutureTask.java:192)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable.runInParallel(SuperActivityOperatorNodePushable.java:212)
        ... 5 more
Caused by: org.apache.hyracks.api.exceptions.HyracksDataException: Index does not have a valid resource ID. Has it been created yet?
        at org.apache.hyracks.storage.am.common.dataflow.IndexDataflowHelper.open(IndexDataflowHelper.java:108)
        at org.apache.hyracks.storage.am.common.dataflow.IndexSearchOperatorNodePushable.open(IndexSearchOperatorNodePushable.java:111)
        at org.apache.hyracks.algebricks.runtime.operators.std.EmptyTupleSourceRuntimeFactory$1.open(EmptyTupleSourceRuntimeFactory.java:51)
        at org.apache.hyracks.algebricks.runtime.operators.meta.AlgebricksMetaOperatorDescriptor$1.initialize(AlgebricksMetaOperatorDescriptor.java:109)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable.lambda$initialize$0(SuperActivityOperatorNodePushable.java:83)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable$$Lambda$4/1452854179.runAction(Unknown Source)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable$1.call(SuperActivityOperatorNodePushable.java:205)
        at org.apache.hyracks.api.rewriter.runtime.SuperActivityOperatorNodePushable$1.call(SuperActivityOperatorNodePushable.java:202)
        at java.util.concurrent.FutureTask.run(FutureTask.java:266)
        ... 3 more

It seems the issue is related to the "distinct by". I have tried the following query also and it works:

use dataverse tpch;

declare function tmp()
{
  for $l in dataset('LineItem')
  where $l.l_commitdate < $l.l_receiptdate
  group by $l_orderkey := $l.l_orderkey with $l
  return { "o_orderkey": $l_orderkey }
}

for $o in dataset('Orders')
for $t in tmp()
where $o.o_orderkey = $t.o_orderkey and 
  $o.o_orderdate >= '1993-07-01' and $o.o_orderdate < '1993-10-01' 
group by $o_orderpriority := $o.o_orderpriority with $o
order by $o_orderpriority
return {
  "order_priority": $o_orderpriority,
  "count": count($o)
}

But I have no clue why "distinct by" is related to the resource ID.
Also, the original query works when I only have two NCs.