Hi,
I tried to reproduce the issue but it is running fine. Are you running this
script in a cluster and any special configuration you have set in
carbon.properties?
The script almost ran 200 times but no problem was observed.
On Sun, Feb 25, 2018 at 1:59 PM, 杨义 <yixu2...@163.com> wrote:
> I'm using carbondata1.3+spark2.1.1+hadoop2.7.1 to do multi update
> operations
> here is the replay step:
>
> import org.apache.spark.sql.SparkSession
> import org.apache.spark.sql.CarbonSession._
> val cc = SparkSession.builder().config(sc.getConf).
> getOrCreateCarbonSession("hdfs://ns1/user/ip_crm")
> // create table
> cc.sql("CREATE TABLE IF NOT EXISTS public.c_compact3 (id string,qqnum
> string,nick string,age string,gender string,auth string,qunnum string,mvcc
> string) STORED BY 'carbondata' TBLPROPERTIES ('SORT_COLUMNS'='id')").show;
> // data prepare
> import org.apache.spark.sql.types._
> import org.apache.spark.sql.Row
> val schema = StructType(StructField("id",StringType,true)::StructField(
> "qqnum",StringType,true)::StructField("nick",StringType,
> true)::StructField("age",StringType,true)::StructField(
> "gender",StringType,true)::StructField("auth",StringType,
> true)::StructField("qunnum",StringType,true)::StructField(
> "mvcc",IntegerType,true)::Nil)
> val data = cc.sparkContext.parallelize(1 to 50000000,4).map { i =>
> Row.fromSeq(Seq(i.toString,i.toString.concat("aaaaaaaa").
> concat(i.toString),"2009-05-27",i.toString.concat("c").
> concat(i.toString),"1","1",i.toString.concat("dddddd").
> concat(i.toString),1))
> }
> cc.createDataFrame(data, schema).createOrReplaceTempView("ddd")
> cc.sql("insert into public.c_compact3 select * from ddd").show;
>
> // update table multi times in while loop
> import scala.util.Random
> var bcnum=1;
> while (true) {
> bcnum=1+bcnum;
> println(bcnum);
> println("111111111");
> var randomNmber = Random.nextInt(1000)
> cc.sql(s"DROP TABLE IF EXISTS cache_compact3").show;
> cc.sql(s"cache table cache_compact3 as select * from
> public.c_compact3 where pmod(cast(id as int),1000)=$randomNmber").show(100,
> false);
> cc.sql("select count(*) from cache_compact3").show;
> cc.sql("update public.c_compact3 a set (a.id
> ,a.qqnum,a.nick,a.age,a.gender,a.auth,a.qunnum,a.mvcc)=(select b.id
> ,b.qqnum,b.nick,b.age,b.gender,b.auth,b.qunnum,b.mvcc from
> cache_compact3 b where b.id=a.id)").show;
> println("222222222");
> Thread.sleep(30000);
> }
>
> after about 30 loop,[Problem in loading segment blocks] error happended.
> then performing select count operations on the table and get exception
> like follows:
>
> scala>cc.sql("select count(*) from public.c_compact3").show;
> 18/02/25 08:49:46 AUDIT CarbonMetaStoreFactory:
> [hdd340][ip_crm][Thread-1]File based carbon metastore is enabled
> Exchange SinglePartition
> +- *HashAggregate(keys=[], functions=[partial_count(1)],
> output=[count#33L])
> +- *BatchedScan CarbonDatasourceHadoopRelation [ Database name :public,
> Table name :c_compact3, Schema
> :Some(StructType(StructField(id,StringType,true),
> StructField(qqnum,StringType,true), StructField(nick,StringType,true),
> StructField(age,StringType,true), StructField(gender,StringType,true),
> StructField(auth,StringType,true), StructField(qunnum,StringType,true),
> StructField(mvcc,StringType,true))) ] public.c_compact3[]
>
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(
> package.scala:56)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(
> ShuffleExchange.scala:112)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> execute$1.apply(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> execute$1.apply(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> executeQuery$1.apply(SparkPlan.scala:135)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(
> RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.
> executeQuery(SparkPlan.scala:132)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(
> WholeStageCodegenExec.scala:235)
> at org.apache.spark.sql.execution.aggregate.HashAggregateExec.inputRDDs(
> HashAggregateExec.scala:141)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(
> WholeStageCodegenExec.scala:368)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> execute$1.apply(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> execute$1.apply(SparkPlan.scala:114)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$
> executeQuery$1.apply(SparkPlan.scala:135)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(
> RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.
> executeQuery(SparkPlan.scala:132)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
> at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.
> scala:225)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:
> 308)
> at org.apache.spark.sql.execution.CollectLimitExec.
> executeCollect(limit.scala:38)
> at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$
> Dataset$$execute$1$1.apply(Dataset.scala:2386)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(
> SQLExecution.scala:57)
> at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2788)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$
> execute$1(Dataset.scala:2385)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$
> collect(Dataset.scala:2392)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.
> scala:2128)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.
> scala:2127)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2818)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:2127)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2342)
> at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:638)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:597)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:606)
> ... 50 elided
> Caused by: java.io.IOException: Problem in loading segment blocks.
> at org.apache.carbondata.core.indexstore.BlockletDataMapIndexStore.
> getAll(BlockletDataMapIndexStore.java:153)
> at org.apache.carbondata.core.indexstore.blockletindex.
> BlockletDataMapFactory.getDataMaps(BlockletDataMapFactory.java:76)
> at org.apache.carbondata.core.datamap.TableDataMap.prune(
> TableDataMap.java:72)
> at org.apache.carbondata.hadoop.api.CarbonTableInputFormat.
> getDataBlocksOfSegment(CarbonTableInputFormat.java:739)
> at org.apache.carbondata.hadoop.api.CarbonTableInputFormat.getSplits(
> CarbonTableInputFormat.java:666)
> at org.apache.carbondata.hadoop.api.CarbonTableInputFormat.getSplits(
> CarbonTableInputFormat.java:426)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.
> getPartitions(CarbonScanRDD.scala:96)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
> at scala.Option.getOrElse(Option.scala:121)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(
> MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
> at scala.Option.getOrElse(Option.scala:121)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(
> MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
> at scala.Option.getOrElse(Option.scala:121)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
> at org.apache.spark.ShuffleDependency.<init>(Dependency.scala:91)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange$.
> prepareShuffleDependency(ShuffleExchange.scala:261)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange.
> prepareShuffleDependency(ShuffleExchange.scala:84)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$
> doExecute$1.apply(ShuffleExchange.scala:121)
> at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$
> doExecute$1.apply(ShuffleExchange.scala:112)
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(
> package.scala:52)
> ... 83 more
> Caused by: java.lang.ArrayIndexOutOfBoundsException: 0
> at org.apache.carbondata.core.datastore.filesystem.
> AbstractDFSCarbonFile.getLocations(AbstractDFSCarbonFile.java:514)
> at org.apache.carbondata.core.indexstore.BlockletDataMapIndexStore.
> getAll(BlockletDataMapIndexStore.java:142)
> ... 109 more
--
Thanks
Sounak
