[ https://issues.apache.org/jira/browse/DRILL-1482?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Parth Chandra updated DRILL-1482: --------------------------------- Assignee: Chris Westin (was: Rahul Challapalli) > Tpch 3 over text files for SF100 causes some of the drillbits(JVM) to crash > --------------------------------------------------------------------------- > > Key: DRILL-1482 > URL: https://issues.apache.org/jira/browse/DRILL-1482 > Project: Apache Drill > Issue Type: Bug > Components: Execution - Flow > Reporter: Rahul Challapalli > Assignee: Chris Westin > Priority: Critical > Fix For: 0.8.0 > > Attachments: drillbit.out, jvm.error > > > git.commit.id.abbrev=5c220e3 > We created views on top of Tpch text data (SF 100) so that we need not modify > the TPCH original queries. Below are the views and the query itself. > {code} > create view nation as select cast(columns[0] as int) n_nationkey, columns[1] > n_name, cast(columns[2] as int) n_regionkey, columns[3] n_comment from > `nation_text`; > create view region as select cast(columns[0] as int) r_regionkey, columns[1] > r_name, columns[2] r_comment from `region_text`; > create view part as select cast(columns[0] as int) p_partkey, columns[1] > p_name, columns[2] p_mfgr, columns[3] p_brand, columns[4] p_type, > cast(columns[5] as int) p_size, columns[6] p_container, cast(columns[7] as > double) p_retailprice, columns[8] p_comment from `part_text`; > create view supplier as select cast(columns[0] as int) s_suppkey, columns[1] > s_name, columns[2] s_address, cast(columns[3] as int) s_nationkey, columns[4] > s_phone, cast(columns[5] as double) s_acctbal, columns[6] s_comment from > `supplier_text`; > create view partsupp as select cast(columns[0] as int) ps_partkey, > cast(columns[1] as int) ps_suppkey, cast(columns[2] as int) ps_availqty, > cast(columns[3] as double) ps_supplycost, columns[4] ps_comment from > `partsupp_text`; > create view customer as select cast(columns[0] as int) c_custkey, columns[1] > c_name, columns[2] c_address, cast(columns[3] as int) c_nationkey, columns[4] > c_phone, cast(columns[5] as double) c_acctbal, columns[6] c_mktsegment, > columns[7] c_comment from `customer_text`; > create view orders as select cast(columns[0] as int) o_orderkey, > cast(columns[1] as int) o_custkey, columns[2] o_orderstatus, cast(columns[3] > as double) o_totalprice, cast(columns[4] as date)o_orderdate, columns[5] > o_orderpriority, columns[6] o_clerk, cast(columns[7] as int) o_shippriority, > columns[8] o_comment from `orders_text`; > create view lineitem as select cast(columns[0] as int) l_orderkey, > cast(columns[1] as int) l_partkey, cast(columns[2] as int) l_suppkey, > cast(columns[3] as int) l_linenumber, cast(columns[4] as double) l_quantity, > cast(columns[5] as double) l_extendedprice, cast(columns[6] as double) > l_discount, cast(columns[7] as double) l_tax, columns[8] l_returnflag, > columns[9] l_linestatus, cast(columns[10] as date) l_shipdate, > cast(columns[11] as date) l_commitdate, cast(columns[12] as date) > l_receiptdate, columns[13] l_shipinstruct, columns[14] l_shipmode, > columns[15] l_comment from `lineitem_text`; > -- TPCH Query 3 > select > l.l_orderkey, > sum(l.l_extendedprice * (1 - l.l_discount)) as revenue, > o.o_orderdate, > o.o_shippriority > from > customer c, > orders o, > lineitem l > where > c.c_mktsegment = 'HOUSEHOLD' > and c.c_custkey = o.o_custkey > and l.l_orderkey = o.o_orderkey > and o.o_orderdate < date '1995-03-25' > and l.l_shipdate > date '1995-03-25' > group by > l.l_orderkey, > o.o_orderdate, > o.o_shippriority > order by > revenue desc, > o.o_orderdate > limit 10; > {code} > The cluster has 8 drillbits running with DRILL_MAX_DIRECT_MEMORY="32G". After > running for around 45 seconds 3 out of the 8 drillbits come down due to a jvm > crash. I attached the log files. Let me know if you need more information. -- This message was sent by Atlassian JIRA (v6.3.4#6332)