[ 
https://issues.apache.org/jira/browse/HIVE-25904?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Denys Kuzmenko updated HIVE-25904:
----------------------------------
    Description: 
{code}
[root@igansperger-hive-tgt-3 ~]# cat test.sh
hive -e 'create database test; create external table test.foo(col1 string);' 2> 
/dev/null
hive -e "select count(*) from sys.tab_col_stats where db_name = 'test' and 
table_name = 'foo'" 2> /dev/null

export JAVA_HOME=/usr/java/jdk1.8.0_232-cloudera
export JAVA_OPTS="-Xmx1g"
export PATH="/root/scala-2.13.8/bin:$JAVA_HOME/bin:$PATH"

export CONF_DIR=/run/cloudera-scm-agent/process/79-hive_on_tez-HIVESERVER2
export CDH_HCAT_HOME=/opt/cloudera/parcels/CDH/lib/hive-hcatalog/
export CDH_HIVE_HOME=/opt/cloudera/parcels/CDH/lib/hive

CLASSPATH="$CLASSPATH:$CONF_DIR/hadoop-conf"
CLASSPATH="$CLASSPATH:$CONF_DIR/hive-conf"
CLASSPATH="$CLASSPATH:$(hadoop classpath)"
CLASSPATH="$CLASSPATH:$CDH_HIVE_HOME/*"
CLASSPATH="$CLASSPATH:$CDH_HIVE_HOME/lib/*"
CLASSPATH="$CLASSPATH:${CDH_HCAT_HOME}/share/webhcat/java-client/hive-webhcat-java-client.jar"
CLASSPATH="$CLASSPATH:${CDH_HCAT_HOME}/share/hcatalog/hive-hcatalog-core.jar"

scala -classpath $CLASSPATH <<-EOF

import org.apache.hadoop.hive.metastore.HiveMetaStoreClient
import org.apache.hadoop.hive.conf.HiveConf
import org.apache.hadoop.hive.metastore.api._

def go() = {
    val conf = new HiveConf()
    val client = new HiveMetaStoreClient(conf)

    val colStatData = new ColumnStatisticsData()
    colStatData.setStringStats(new StringColumnStatsData(3, 3.0, 0, 1))
    val colStatsObj = new ColumnStatisticsObj("col1", "string", colStatData)
    val colStatsObjs = java.util.Arrays.asList(colStatsObj)
    val colStatsDesc = new ColumnStatisticsDesc(true, "test", "foo")
    val colStats = new ColumnStatistics(colStatsDesc, colStatsObjs)
    colStats.setEngine("hive")

    client.updateTableColumnStatistics(colStats)
    println("SUCCESS")
}

val t1 = new Thread(() => go())
val t2 = new Thread(() => go())
t1.start()
t2.start()

t1.join()
t2.join()

go()

EOF

hive -e "select count(*) from sys.tab_col_stats where db_name = 'test' and 
table_name = 'foo'" 2> /dev/null
{code}

This produces (minus logging):
{code}
[root@igansperger-hive-tgt-3 ~]# sh test.sh
+------+
| _c0  |
+------+
| 0    |
+------+

Welcome to Scala 2.13.8 (OpenJDK 64-Bit Server VM, Java 1.8.0_232).
Type in expressions for evaluation. Or try :help.

SUCCESS
SUCCESS
org.apache.hadoop.hive.metastore.api.MetaException: Unexpected 2 statistics for 
1 columns
  at 
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result$update_table_column_statistics_req_resultStandardScheme.read(ThriftHiveMetastore.java)
  at 
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result$update_table_column_statistics_req_resultStandardScheme.read(ThriftHiveMetastore.java)
  at 
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result.read(ThriftHiveMetastore.java)
  at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:86)
  at 
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_update_table_column_statistics_req(ThriftHiveMetastore.java:4597)
  at 
org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.update_table_column_statistics_req(ThriftHiveMetastore.java:4584)
  at 
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.updateTableColumnStatistics(HiveMetaStoreClient.java:2846)
  at go(<console>:13)
  ... 32 elided

scala>
scala> :quit

+------+
| _c0  |
+------+
| 2    |
+------+
{code}

> ObjectStore's updateTableColumnStatistics is not ThreadSafe
> -----------------------------------------------------------
>
>                 Key: HIVE-25904
>                 URL: https://issues.apache.org/jira/browse/HIVE-25904
>             Project: Hive
>          Issue Type: Bug
>            Reporter: Denys Kuzmenko
>            Priority: Major
>
> {code}
> [root@igansperger-hive-tgt-3 ~]# cat test.sh
> hive -e 'create database test; create external table test.foo(col1 string);' 
> 2> /dev/null
> hive -e "select count(*) from sys.tab_col_stats where db_name = 'test' and 
> table_name = 'foo'" 2> /dev/null
> export JAVA_HOME=/usr/java/jdk1.8.0_232-cloudera
> export JAVA_OPTS="-Xmx1g"
> export PATH="/root/scala-2.13.8/bin:$JAVA_HOME/bin:$PATH"
> export CONF_DIR=/run/cloudera-scm-agent/process/79-hive_on_tez-HIVESERVER2
> export CDH_HCAT_HOME=/opt/cloudera/parcels/CDH/lib/hive-hcatalog/
> export CDH_HIVE_HOME=/opt/cloudera/parcels/CDH/lib/hive
> CLASSPATH="$CLASSPATH:$CONF_DIR/hadoop-conf"
> CLASSPATH="$CLASSPATH:$CONF_DIR/hive-conf"
> CLASSPATH="$CLASSPATH:$(hadoop classpath)"
> CLASSPATH="$CLASSPATH:$CDH_HIVE_HOME/*"
> CLASSPATH="$CLASSPATH:$CDH_HIVE_HOME/lib/*"
> CLASSPATH="$CLASSPATH:${CDH_HCAT_HOME}/share/webhcat/java-client/hive-webhcat-java-client.jar"
> CLASSPATH="$CLASSPATH:${CDH_HCAT_HOME}/share/hcatalog/hive-hcatalog-core.jar"
> scala -classpath $CLASSPATH <<-EOF
> import org.apache.hadoop.hive.metastore.HiveMetaStoreClient
> import org.apache.hadoop.hive.conf.HiveConf
> import org.apache.hadoop.hive.metastore.api._
> def go() = {
>     val conf = new HiveConf()
>     val client = new HiveMetaStoreClient(conf)
>     val colStatData = new ColumnStatisticsData()
>     colStatData.setStringStats(new StringColumnStatsData(3, 3.0, 0, 1))
>     val colStatsObj = new ColumnStatisticsObj("col1", "string", colStatData)
>     val colStatsObjs = java.util.Arrays.asList(colStatsObj)
>     val colStatsDesc = new ColumnStatisticsDesc(true, "test", "foo")
>     val colStats = new ColumnStatistics(colStatsDesc, colStatsObjs)
>     colStats.setEngine("hive")
>     client.updateTableColumnStatistics(colStats)
>     println("SUCCESS")
> }
> val t1 = new Thread(() => go())
> val t2 = new Thread(() => go())
> t1.start()
> t2.start()
> t1.join()
> t2.join()
> go()
> EOF
> hive -e "select count(*) from sys.tab_col_stats where db_name = 'test' and 
> table_name = 'foo'" 2> /dev/null
> {code}
> This produces (minus logging):
> {code}
> [root@igansperger-hive-tgt-3 ~]# sh test.sh
> +------+
> | _c0  |
> +------+
> | 0    |
> +------+
> Welcome to Scala 2.13.8 (OpenJDK 64-Bit Server VM, Java 1.8.0_232).
> Type in expressions for evaluation. Or try :help.
> SUCCESS
> SUCCESS
> org.apache.hadoop.hive.metastore.api.MetaException: Unexpected 2 statistics 
> for 1 columns
>   at 
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result$update_table_column_statistics_req_resultStandardScheme.read(ThriftHiveMetastore.java)
>   at 
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result$update_table_column_statistics_req_resultStandardScheme.read(ThriftHiveMetastore.java)
>   at 
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$update_table_column_statistics_req_result.read(ThriftHiveMetastore.java)
>   at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:86)
>   at 
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.recv_update_table_column_statistics_req(ThriftHiveMetastore.java:4597)
>   at 
> org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.update_table_column_statistics_req(ThriftHiveMetastore.java:4584)
>   at 
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient.updateTableColumnStatistics(HiveMetaStoreClient.java:2846)
>   at go(<console>:13)
>   ... 32 elided
> scala>
> scala> :quit
> +------+
> | _c0  |
> +------+
> | 2    |
> +------+
> {code}



--
This message was sent by Atlassian Jira
(v8.20.1#820001)

Reply via email to