Hi,
My Steps:
### HIVE
CREATE TABLE CUSTOMER (
C_CUSTKEY BIGINT,
C_NAME VARCHAR(25),
C_ADDRESS VARCHAR(40),
C_NATIONKEY BIGINT,
C_PHONE VARCHAR(15),
C_ACCTBAL DECIMAL,
C_MKTSEGMENT VARCHAR(10),
C_COMMENT VARCHAR(117)
) row format serde 'com.bizo.hive.serde.csv.CSVSerde';
LOAD DATA LOCAL INPATH '/usr/local/pdgf/output/CUSTOMER.csv' INTO TABLE
CUSTOMER;
CREATE TABLE ORDERS (
O_ORDERKEY BIGINT,
O_CUSTKEY BIGINT,
O_ORDERSTATUS string,
O_TOTALPRICE DECIMAL,
O_ORDERDATE STRING,
O_ORDERPRIORITY VARCHAR(15),
O_CLERK VARCHAR(15),
O_SHIPPRIORITY INT,
O_COMMENT VARCHAR(79)
) ROW FORMAT serde 'com.bizo.hive.serde.csv.CSVSerde’;
LOAD DATA LOCAL INPATH '/usr/local/pdgf/output/ORDERS.csv' INTO TABLE ORDERS;
CREATE TABLE LINEITEM (
L_ORDERKEY BIGINT,
L_PARTKEY BIGINT,
L_SUPPKEY BIGINT,
L_LINENUMBER INT,
L_QUANTITY DECIMAL,
L_EXTENDEDPRICE DECIMAL,
L_DISCOUNT DECIMAL,
L_TAX DECIMAL,
L_SHIPDATE STRING,
L_COMMITDATE STRING,
L_RECEIPTDATE STRING,
L_RETURNFLAG STRING,
L_LINESTATUS STRING,
L_SHIPINSTRUCT VARCHAR(25),
L_SHIPMODE VARCHAR(10),
L_COMMENT VARCHAR(44)
) ROW FORMAT serde 'com.bizo.hive.serde.csv.CSVSerde';
LOAD DATA LOCAL INPATH 'vpdgf/output/LINEITEM.csv' INTO TABLE LINEITEM;
… (same for other tables)
hive> add jar /hadoop/hive/csv-serde-1.1.2-0.11.0-all.jar;
hive> select l_orderkey, sum(l_extendedprice*(1-l_discount)) as revenue,
o_orderdate, o_shippriority from customer c join orders o on c.c_mktsegment =
'BUILDING' and c.c_custkey = o.o_custkey join lineitem l on l.l_orderkey =
o.o_orderkey where o_orderdate < '1995-03-15' and l_shipdate > '1995-03-15'
group by l_orderkey, o_orderdate, o_shippriority order by revenue desc,
o_orderdate limit 10;
MapReduce Total cumulative CPU time: 25 seconds 110 msec
Ended Job = job_1414101999739_0004
MapReduce Jobs Launched:
Job 0: Map: 26 Reduce: 7 Cumulative CPU: 378.14 sec HDFS Read: 6502040850
HDFS Write: 173752818 SUCCESS
Job 1: Map: 100 Reduce: 27 Cumulative CPU: 1376.06 sec HDFS Read:
26273646797 HDFS Write: 183687996 SUCCESS
Job 2: Map: 3 Reduce: 1 Cumulative CPU: 32.25 sec HDFS Read: 183694290
HDFS Write: 183706480 SUCCESS
Job 3: Map: 1 Reduce: 1 Cumulative CPU: 25.11 sec HDFS Read: 183707750
HDFS Write: 349 SUCCESS
Total MapReduce CPU Time Spent: 30 minutes 11 seconds 560 msec
### Run the same SQL in Spark
scala> val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc)
scala> sqlContext.sql("""select l_orderkey, sum(l_extendedprice*(1-l_discount))
as revenue, o_orderdate, o_shippriority from customer c join orders o on
c.c_mktsegment = 'BUILDING' and c.c_custkey = o.o_custkey join lineitem l on
l.l_orderkey = o.o_orderkey where o_orderdate < '1995-03-15' and l_shipdate >
'1995-03-15' group by l_orderkey, o_orderdate, o_shippriority order by revenue
desc, o_orderdate limit 10""").collect().foreach(println);
java.lang.ClassCastException: java.lang.String cannot be cast to
scala.math.BigDecimal
scala.math.Numeric$BigDecimalIsFractional$.minus(Numeric.scala:182)
org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:114)
org.apache.spark.sql.catalyst.expressions.Subtract.eval(arithmetic.scala:64)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
org.apache.spark.sql.catalyst.expressions.Multiply.eval(arithmetic.scala:70)
org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:47)
org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:58)
org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:69)
org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:433)
org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167)
org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at
scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)14/10/25
06:50:15 WARN TaskSetManager: Lost task 7.3 in stage 5.0 (TID 575,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 24.2 in stage 5.0 (TID 560,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 22.2 in stage 5.0 (TID 561,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 20.2 in stage 5.0 (TID 564,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 13.2 in stage 5.0 (TID 562,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 27.2 in stage 5.0 (TID 565,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 WARN TaskSetManager: Lost task 34.2 in stage 5.0 (TID 568,
m137.emblocsoft.net): TaskKilled (killed intentionally)
14/10/25 06:50:15 INFO TaskSchedulerImpl: Removed TaskSet 5.0, whose tasks have
all completed, from pool
Regards
Arthur
On 24 Oct, 2014, at 6:56 am, Michael Armbrust <[email protected]> wrote:
> Can you show the DDL for the table? It looks like the SerDe might be saying
> it will produce a decimal type but is actually producing a string.
>
> On Thu, Oct 23, 2014 at 3:17 PM, [email protected]
> <[email protected]> wrote:
> Hi
>
> My Spark is 1.1.0 and Hive is 0.12, I tried to run the same query in both
> Hive-0.12.0 then Spark-1.1.0, HiveQL works while SparkSQL failed.
>
>
> hive> select l_orderkey, sum(l_extendedprice*(1-l_discount)) as revenue,
> o_orderdate, o_shippriority from customer c join orders o on c.c_mktsegment =
> 'BUILDING' and c.c_custkey = o.o_custkey join lineitem l on l.l_orderkey =
> o.o_orderkey where o_orderdate < '1995-03-15' and l_shipdate > '1995-03-15'
> group by l_orderkey, o_orderdate, o_shippriority order by revenue desc,
> o_orderdate limit 10;
> Ended Job = job_1414067367860_0011
> MapReduce Jobs Launched:
> Job 0: Map: 1 Reduce: 1 Cumulative CPU: 2.0 sec HDFS Read: 261 HDFS
> Write: 96 SUCCESS
> Job 1: Map: 1 Reduce: 1 Cumulative CPU: 0.88 sec HDFS Read: 458 HDFS
> Write: 0 SUCCESS
> Total MapReduce CPU Time Spent: 2 seconds 880 msec
> OK
> Time taken: 38.771 seconds
>
>
> scala> sqlContext.sql("""select l_orderkey,
> sum(l_extendedprice*(1-l_discount)) as revenue, o_orderdate, o_shippriority
> from customer c join orders o on c.c_mktsegment = 'BUILDING' and c.c_custkey
> = o.o_custkey join lineitem l on l.l_orderkey = o.o_orderkey where
> o_orderdate < '1995-03-15' and l_shipdate > '1995-03-15' group by l_orderkey,
> o_orderdate, o_shippriority order by revenue desc, o_orderdate limit
> 10""").collect().foreach(println);
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 14 in
> stage 5.0 failed 4 times, most recent failure: Lost task 14.3 in stage 5.0
> (TID 568, m34): java.lang.ClassCastException: java.lang.String cannot be cast
> to scala.math.BigDecimal
> scala.math.Numeric$BigDecimalIsFractional$.minus(Numeric.scala:182)
>
> org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
>
> org.apache.spark.sql.catalyst.expressions.Subtract$$anonfun$eval$3.apply(arithmetic.scala:64)
>
> org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:114)
>
> org.apache.spark.sql.catalyst.expressions.Subtract.eval(arithmetic.scala:64)
>
> org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
>
> org.apache.spark.sql.catalyst.expressions.Multiply.eval(arithmetic.scala:70)
>
> org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:47)
>
> org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:108)
>
> org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:58)
>
> org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:69)
>
> org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:433)
>
> org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167)
>
> org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151)
> org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
> org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> org.apache.spark.scheduler.Task.run(Task.scala:54)
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
>
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> java.lang.Thread.run(Thread.java:745)
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
> at akka.actor.ActorCell.invoke(ActorCell.scala:456)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
> at akka.dispatch.Mailbox.run(Mailbox.scala:219)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
> at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at
> scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
>
>
> Regards
> Arthur
>
>
>
>
>
>