You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/03/20 19:57:14 UTC
hive git commit: HIVE-18984: Make time window configurable per
materialized view (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Repository: hive
Updated Branches:
refs/heads/master 8f804af05 -> a16e8e9e4
HIVE-18984: Make time window configurable per materialized view (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/a16e8e9e
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/a16e8e9e
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/a16e8e9e
Branch: refs/heads/master
Commit: a16e8e9e4d1111d504051b836d43ed795de054b3
Parents: 8f804af
Author: Jesus Camacho Rodriguez <jc...@apache.org>
Authored: Fri Mar 16 15:48:17 2018 -0700
Committer: Jesus Camacho Rodriguez <jc...@apache.org>
Committed: Tue Mar 20 12:56:17 2018 -0700
----------------------------------------------------------------------
.../org/apache/hadoop/hive/conf/Constants.java | 2 +
.../org/apache/hadoop/hive/conf/HiveConf.java | 2 +-
.../apache/hadoop/hive/ql/metadata/Hive.java | 22 +-
.../hadoop/hive/ql/parse/CalcitePlanner.java | 2 +-
...terialized_view_create_rewrite_time_window.q | 99 +++
...alized_view_create_rewrite_time_window.q.out | 830 +++++++++++++++++++
6 files changed, 949 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/common/src/java/org/apache/hadoop/hive/conf/Constants.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/conf/Constants.java b/common/src/java/org/apache/hadoop/hive/conf/Constants.java
index 10aaee1..60a9b9e 100644
--- a/common/src/java/org/apache/hadoop/hive/conf/Constants.java
+++ b/common/src/java/org/apache/hadoop/hive/conf/Constants.java
@@ -49,4 +49,6 @@ public class Constants {
public static final String HIVE_SERVER2_JOB_CREDSTORE_PASSWORD_ENVVAR = "HIVE_JOB_CREDSTORE_PASSWORD";
public static final String HADOOP_CREDENTIAL_PASSWORD_ENVVAR = "HADOOP_CREDSTORE_PASSWORD";
public static final String HADOOP_CREDENTIAL_PROVIDER_PATH_CONFIG = "hadoop.security.credential.provider.path";
+
+ public static final String MATERIALIZED_VIEW_REWRITING_TIME_WINDOW = "rewriting.time.window";
}
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
index f8e715d..dd94d4d 100644
--- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
+++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
@@ -4135,7 +4135,7 @@ public class HiveConf extends Configuration {
return getSizeVar(this, var);
}
- private static TimeUnit getDefaultTimeUnit(ConfVars var) {
+ public static TimeUnit getDefaultTimeUnit(ConfVars var) {
TimeUnit inputUnit = null;
if (var.validator instanceof TimeValidator) {
inputUnit = ((TimeValidator)var.validator).getTimeUnit();
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java b/ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java
index 5a7e297..da690b4 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java
@@ -24,6 +24,7 @@ import com.google.common.collect.Lists;
import com.google.common.collect.Maps;
import com.google.common.collect.Sets;
import com.google.common.util.concurrent.ThreadFactoryBuilder;
+import static org.apache.hadoop.hive.conf.Constants.MATERIALIZED_VIEW_REWRITING_TIME_WINDOW;
import static org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.META_TABLE_STORAGE;
import static org.apache.hadoop.hive.serde.serdeConstants.SERIALIZATION_FORMAT;
import static org.apache.hadoop.hive.serde.serdeConstants.STRING_TYPE_NAME;
@@ -74,6 +75,7 @@ import org.apache.hadoop.hive.common.StatsSetupConst;
import org.apache.hadoop.hive.common.classification.InterfaceAudience.LimitedPrivate;
import org.apache.hadoop.hive.common.classification.InterfaceStability.Unstable;
import org.apache.hadoop.hive.common.log.InPlaceUpdate;
+import org.apache.hadoop.hive.conf.Constants;
import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.hive.conf.HiveConf.ConfVars;
import org.apache.hadoop.hive.io.HdfsUtils;
@@ -1299,11 +1301,11 @@ public class Hive {
* @return the list of materialized views available for rewriting
* @throws HiveException
*/
- public List<RelOptMaterialization> getValidMaterializedViews() throws HiveException {
- final long diff =
+ public List<RelOptMaterialization> getValidMaterializedViews(boolean materializedViewRebuild) throws HiveException {
+ final long defaultDiff =
HiveConf.getTimeVar(conf, HiveConf.ConfVars.HIVE_MATERIALIZED_VIEW_REWRITING_TIME_WINDOW,
TimeUnit.MILLISECONDS);
- final long minTime = System.currentTimeMillis() - diff;
+ final long currentTime = System.currentTimeMillis();
try {
// Final result
List<RelOptMaterialization> result = new ArrayList<>();
@@ -1326,9 +1328,17 @@ public class Hive {
" ignored for rewriting as there was no information loaded in the invalidation cache");
continue;
}
+ // Check if materialization defined its own invalidation time window
+ String timeWindowString = materializedViewTable.getProperty(MATERIALIZED_VIEW_REWRITING_TIME_WINDOW);
+ long diff = org.apache.commons.lang.StringUtils.isEmpty(timeWindowString) ? defaultDiff :
+ HiveConf.toTime(timeWindowString,
+ HiveConf.getDefaultTimeUnit(HiveConf.ConfVars.HIVE_MATERIALIZED_VIEW_REWRITING_TIME_WINDOW),
+ TimeUnit.MILLISECONDS);
+
long invalidationTime = materializationInvalidationInfo.getInvalidationTime();
- // If the limit is not met, we do not add the materialized view
- if (diff == 0L) {
+ // If the limit is not met, we do not add the materialized view.
+ // If we are doing a rebuild, we do not consider outdated materialized views either.
+ if (diff == 0L || materializedViewRebuild) {
if (invalidationTime != 0L) {
// If parameter is zero, materialized view cannot be outdated at all
LOG.debug("Materialized view " + materializedViewTable.getFullyQualifiedName() +
@@ -1336,7 +1346,7 @@ public class Hive {
continue;
}
} else {
- if (invalidationTime != 0 && minTime > invalidationTime) {
+ if (invalidationTime != 0 && invalidationTime > currentTime - diff) {
LOG.debug("Materialized view " + materializedViewTable.getFullyQualifiedName() +
" ignored for rewriting as its contents are outdated");
continue;
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
index 3520d90..92e2f3b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
@@ -1547,7 +1547,7 @@ public class CalcitePlanner extends SemanticAnalyzer {
// Add views to planner
List<RelOptMaterialization> materializations = new ArrayList<>();
try {
- materializations = Hive.get().getValidMaterializedViews();
+ materializations = Hive.get().getValidMaterializedViews(rewrittenRebuild);
// We need to use the current cluster for the scan operator on views,
// otherwise the planner will throw an Exception (different planners)
materializations = Lists.transform(materializations,
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
new file mode 100644
index 0000000..0755d39
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
@@ -0,0 +1,99 @@
+set hive.support.concurrency=true;
+set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
+set hive.strict.checks.cartesian.product=false;
+set hive.materializedview.rewriting=true;
+
+create table cmv_basetable (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
+
+insert into cmv_basetable values
+ (1, 'alfred', 10.30, 2),
+ (2, 'bob', 3.14, 3),
+ (2, 'bonnie', 172342.2, 3),
+ (3, 'calvin', 978.76, 3),
+ (3, 'charlie', 9.8, 1);
+
+analyze table cmv_basetable compute statistics for columns;
+
+create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
+
+insert into cmv_basetable_2 values
+ (1, 'alfred', 10.30, 2),
+ (3, 'calvin', 978.76, 3);
+
+analyze table cmv_basetable_2 compute statistics for columns;
+
+-- CREATE VIEW WITH REWRITE DISABLED
+EXPLAIN
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+DESCRIBE FORMATTED cmv_mat_view;
+
+-- CANNOT USE THE VIEW, IT IS DISABLED FOR REWRITE
+EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+insert into cmv_basetable_2 values
+ (3, 'charlie', 15.8, 1);
+
+analyze table cmv_basetable_2 compute statistics for columns;
+
+-- ENABLE FOR REWRITE
+EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE;
+
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE;
+
+DESCRIBE FORMATTED cmv_mat_view;
+
+-- CAN USE THE MATERIALIZED VIEW, AS TIME WINDOW IS HUGE
+-- WE GET OUTDATED RESULTS
+EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+-- REBUILD
+EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD;
+
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD;
+
+DESCRIBE FORMATTED cmv_mat_view;
+
+-- CAN USE IT AGAIN
+EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c;
+
+drop materialized view cmv_mat_view;
http://git-wip-us.apache.org/repos/asf/hive/blob/a16e8e9e/ql/src/test/results/clientpositive/materialized_view_create_rewrite_time_window.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/materialized_view_create_rewrite_time_window.q.out b/ql/src/test/results/clientpositive/materialized_view_create_rewrite_time_window.q.out
new file mode 100644
index 0000000..bfbac3f
--- /dev/null
+++ b/ql/src/test/results/clientpositive/materialized_view_create_rewrite_time_window.q.out
@@ -0,0 +1,830 @@
+PREHOOK: query: create table cmv_basetable (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_basetable
+POSTHOOK: query: create table cmv_basetable (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_basetable
+PREHOOK: query: insert into cmv_basetable values
+ (1, 'alfred', 10.30, 2),
+ (2, 'bob', 3.14, 3),
+ (2, 'bonnie', 172342.2, 3),
+ (3, 'calvin', 978.76, 3),
+ (3, 'charlie', 9.8, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable
+POSTHOOK: query: insert into cmv_basetable values
+ (1, 'alfred', 10.30, 2),
+ (2, 'bob', 3.14, 3),
+ (2, 'bonnie', 172342.2, 3),
+ (3, 'calvin', 978.76, 3),
+ (3, 'charlie', 9.8, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable
+POSTHOOK: Lineage: cmv_basetable.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Output: default@cmv_basetable
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Output: default@cmv_basetable
+#### A masked pattern was here ####
+PREHOOK: query: create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_basetable_2
+PREHOOK: query: insert into cmv_basetable_2 values
+ (1, 'alfred', 10.30, 2),
+ (3, 'calvin', 978.76, 3)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: insert into cmv_basetable_2 values
+ (1, 'alfred', 10.30, 2),
+ (3, 'calvin', 978.76, 3)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable_2
+POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+PREHOOK: query: EXPLAIN
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: query: EXPLAIN
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-5 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-5
+ Stage-6 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 2 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(10,2))
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.cmv_mat_view
+
+ Stage: Stage-0
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-5
+ Create View Operator:
+ Create View
+ columns: a int, c decimal(10,2)
+ table properties:
+ rewriting.time.window 300s
+ expanded text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ name: default.cmv_mat_view
+ original text: SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+
+ Stage: Stage-6
+ Materialized View Work
+
+PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES('rewriting.time.window'='300s') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_mat_view
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 2
+ rawDataSize 232
+ rewriting.time.window 300s
+ totalSize 325
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: No
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 2 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((c > 10.1) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(10,2))
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+1
+3
+PREHOOK: query: insert into cmv_basetable_2 values
+ (3, 'charlie', 15.8, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: insert into cmv_basetable_2 values
+ (3, 'charlie', 15.8, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable_2
+POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+POSTHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Alter Materialized View Operator:
+ Alter Materialized View
+ name: default.cmv_mat_view
+ operation: UPDATE_REWRITE_FLAG
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+POSTHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 2
+ rawDataSize 232
+ rewriting.time.window 300s
+ totalSize 325
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: Yes
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+1
+3
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-6 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 3 Data size: 727 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(10,2))
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.cmv_mat_view
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: a, c
+ Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.cmv_mat_view
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view
+
+ Stage: Stage-6
+ Materialized View Work
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Lineage: cmv_mat_view.a SIMPLE [(cmv_basetable)cmv_basetable.FieldSchema(name:a, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.c SIMPLE [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
+ numFiles 1
+ numRows 3
+ rawDataSize 348
+ rewriting.time.window 300s
+ totalSize 332
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: Yes
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+1
+3
+3
+PREHOOK: query: drop materialized view cmv_mat_view
+PREHOOK: type: DROP_MATERIALIZED_VIEW
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: drop materialized view cmv_mat_view
+POSTHOOK: type: DROP_MATERIALIZED_VIEW
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view