hadoop-hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From zs...@apache.org
Subject svn commit: r752034 [1/2] - in /hadoop/hive/trunk/ql/src/test: queries/clientpositive/ results/clientpositive/
Date Tue, 10 Mar 2009 10:23:41 GMT
Author: zshao
Date: Tue Mar 10 10:23:40 2009
New Revision: 752034

URL: http://svn.apache.org/viewvc?rev=752034&view=rev
Log:
HIVE-223. Test cases for single map-reduce group-by using map-side aggregation. (Namit Jain via zshao)

Added:
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_nomap.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_noskew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map_skew.q
    hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_noskew.q
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby7_map.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby7_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby7_noskew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby8_map.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby8_map_skew.q.out
    hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby8_noskew.q.out

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_nomap.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_nomap.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_nomap.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_nomap.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,12 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=false;
+set hive.groupby.mapaggr.checkinterval=20;
+
+CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,12 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby1_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,12 @@
+set hive.map.aggr=false;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest_g1(key INT, value DOUBLE) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key;
+
+SELECT dest_g1.* FROM dest_g1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,14 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key STRING, c1 INT, c2 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1);
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby2_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,14 @@
+set hive.map.aggr=false;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1);
+
+SELECT dest_g2.* FROM dest_g2;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,14 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5));
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5));
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby3_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,15 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5));
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5));
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,12 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key INT) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1);
+
+FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1);
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby4_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,16 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1);
+
+SELECT dest1.* FROM dest1;
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,12 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key INT) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key);
+
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key);
+
+SELECT dest1.* FROM dest1;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby5_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,20 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+INSERT OVERWRITE TABLE dest1 
+SELECT src.key, sum(substr(src.value,5)) 
+FROM src
+GROUP BY src.key;
+
+INSERT OVERWRITE TABLE dest1 
+SELECT src.key, sum(substr(src.value,5)) 
+FROM src
+GROUP BY src.key;
+
+SELECT dest1.* FROM dest1;
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,16 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+SELECT dest1.* FROM dest1;
+
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,16 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+SELECT dest1.* FROM dest1;
+
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby6_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,17 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1);
+
+SELECT dest1.* FROM dest1;
+
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,21 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+SET hive.exec.compress.intermediate=true;
+SET hive.exec.compress.output=true; 
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,21 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+SET hive.exec.compress.intermediate=true;
+SET hive.exec.compress.output=true; 
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby7_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,22 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+SET hive.exec.compress.intermediate=true;
+SET hive.exec.compress.output=true; 
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, sum(SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,19 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map_skew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map_skew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map_skew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_map_skew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,19 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=true;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;
+

Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_noskew.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_noskew.q?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_noskew.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/groupby8_noskew.q Tue Mar 10 10:23:40 2009
@@ -0,0 +1,20 @@
+set hive.map.aggr=false;
+
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE DEST1(key INT, value STRING) STORED AS TEXTFILE;
+CREATE TABLE DEST2(key INT, value STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+FROM SRC
+INSERT OVERWRITE TABLE DEST1 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
+INSERT OVERWRITE TABLE DEST2 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key;
+
+SELECT DEST1.* FROM DEST1;
+SELECT DEST2.* FROM DEST2;
+

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,374 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_COLREF src key)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5)))) (TOK_GROUPBY (TOK_COLREF src key))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Group By Operator
+              aggregations:
+                    expr: sum(UDFToDouble(substr(value, 5)))
+              keys:
+                    expr: key
+                    type: string
+              mode: hash
+              Reduce Output Operator
+                key expressions:
+                      expr: 0
+                      type: string
+                sort order: +
+                Map-reduce partition columns:
+                      expr: 0
+                      type: string
+                tag: -1
+                value expressions:
+                      expr: 1
+                      type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 1
+                  type: double
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0	0.0
+10	10.0
+100	200.0
+103	206.0
+104	208.0
+105	105.0
+11	11.0
+111	111.0
+113	226.0
+114	114.0
+116	116.0
+118	236.0
+119	357.0
+12	24.0
+120	240.0
+125	250.0
+126	126.0
+128	384.0
+129	258.0
+131	131.0
+133	133.0
+134	268.0
+136	136.0
+137	274.0
+138	552.0
+143	143.0
+145	145.0
+146	292.0
+149	298.0
+15	30.0
+150	150.0
+152	304.0
+153	153.0
+155	155.0
+156	156.0
+157	157.0
+158	158.0
+160	160.0
+162	162.0
+163	163.0
+164	328.0
+165	330.0
+166	166.0
+167	501.0
+168	168.0
+169	676.0
+17	17.0
+170	170.0
+172	344.0
+174	348.0
+175	350.0
+176	352.0
+177	177.0
+178	178.0
+179	358.0
+18	36.0
+180	180.0
+181	181.0
+183	183.0
+186	186.0
+187	561.0
+189	189.0
+19	19.0
+190	190.0
+191	382.0
+192	192.0
+193	579.0
+194	194.0
+195	390.0
+196	196.0
+197	394.0
+199	597.0
+2	2.0
+20	20.0
+200	400.0
+201	201.0
+202	202.0
+203	406.0
+205	410.0
+207	414.0
+208	624.0
+209	418.0
+213	426.0
+214	214.0
+216	432.0
+217	434.0
+218	218.0
+219	438.0
+221	442.0
+222	222.0
+223	446.0
+224	448.0
+226	226.0
+228	228.0
+229	458.0
+230	1150.0
+233	466.0
+235	235.0
+237	474.0
+238	476.0
+239	478.0
+24	48.0
+241	241.0
+242	484.0
+244	244.0
+247	247.0
+248	248.0
+249	249.0
+252	252.0
+255	510.0
+256	512.0
+257	257.0
+258	258.0
+26	52.0
+260	260.0
+262	262.0
+263	263.0
+265	530.0
+266	266.0
+27	27.0
+272	544.0
+273	819.0
+274	274.0
+275	275.0
+277	1108.0
+278	556.0
+28	28.0
+280	560.0
+281	562.0
+282	564.0
+283	283.0
+284	284.0
+285	285.0
+286	286.0
+287	287.0
+288	576.0
+289	289.0
+291	291.0
+292	292.0
+296	296.0
+298	894.0
+30	30.0
+302	302.0
+305	305.0
+306	306.0
+307	614.0
+308	308.0
+309	618.0
+310	310.0
+311	933.0
+315	315.0
+316	948.0
+317	634.0
+318	954.0
+321	642.0
+322	644.0
+323	323.0
+325	650.0
+327	981.0
+33	33.0
+331	662.0
+332	332.0
+333	666.0
+335	335.0
+336	336.0
+338	338.0
+339	339.0
+34	34.0
+341	341.0
+342	684.0
+344	688.0
+345	345.0
+348	1740.0
+35	105.0
+351	351.0
+353	706.0
+356	356.0
+360	360.0
+362	362.0
+364	364.0
+365	365.0
+366	366.0
+367	734.0
+368	368.0
+369	1107.0
+37	74.0
+373	373.0
+374	374.0
+375	375.0
+377	377.0
+378	378.0
+379	379.0
+382	764.0
+384	1152.0
+386	386.0
+389	389.0
+392	392.0
+393	393.0
+394	394.0
+395	790.0
+396	1188.0
+397	794.0
+399	798.0
+4	4.0
+400	400.0
+401	2005.0
+402	402.0
+403	1209.0
+404	808.0
+406	1624.0
+407	407.0
+409	1227.0
+41	41.0
+411	411.0
+413	826.0
+414	828.0
+417	1251.0
+418	418.0
+419	419.0
+42	84.0
+421	421.0
+424	848.0
+427	427.0
+429	858.0
+43	43.0
+430	1290.0
+431	1293.0
+432	432.0
+435	435.0
+436	436.0
+437	437.0
+438	1314.0
+439	878.0
+44	44.0
+443	443.0
+444	444.0
+446	446.0
+448	448.0
+449	449.0
+452	452.0
+453	453.0
+454	1362.0
+455	455.0
+457	457.0
+458	916.0
+459	918.0
+460	460.0
+462	924.0
+463	926.0
+466	1398.0
+467	467.0
+468	1872.0
+469	2345.0
+47	47.0
+470	470.0
+472	472.0
+475	475.0
+477	477.0
+478	956.0
+479	479.0
+480	1440.0
+481	481.0
+482	482.0
+483	483.0
+484	484.0
+485	485.0
+487	487.0
+489	1956.0
+490	490.0
+491	491.0
+492	984.0
+493	493.0
+494	494.0
+495	495.0
+496	496.0
+497	497.0
+498	1494.0
+5	15.0
+51	102.0
+53	53.0
+54	54.0
+57	57.0
+58	116.0
+64	64.0
+65	65.0
+66	66.0
+67	134.0
+69	69.0
+70	210.0
+72	144.0
+74	74.0
+76	152.0
+77	77.0
+78	78.0
+8	8.0
+80	80.0
+82	82.0
+83	166.0
+84	168.0
+85	85.0
+86	86.0
+87	87.0
+9	9.0
+90	270.0
+92	92.0
+95	190.0
+96	96.0
+97	194.0
+98	196.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,407 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_COLREF src key)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5)))) (TOK_GROUPBY (TOK_COLREF src key))))
+
+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
+      Alias -> Map Operator Tree:
+        src 
+            Group By Operator
+              aggregations:
+                    expr: sum(UDFToDouble(substr(value, 5)))
+              keys:
+                    expr: key
+                    type: string
+              mode: hash
+              Reduce Output Operator
+                key expressions:
+                      expr: 0
+                      type: string
+                sort order: +
+                Map-reduce partition columns:
+                      expr: rand()
+                      type: double
+                tag: -1
+                value expressions:
+                      expr: 1
+                      type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: partial2
+          File Output Operator
+            compressed: false
+            GlobalTableId: 0
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.mapred.SequenceFileOutputFormat
+                name: binary_table
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        /data/users/njain/hive1/hive/build/ql/tmp/98848080/907077792.10001 
+          Reduce Output Operator
+            key expressions:
+                  expr: 0
+                  type: string
+            sort order: +
+            Map-reduce partition columns:
+                  expr: 0
+                  type: string
+            tag: -1
+            value expressions:
+                  expr: 1
+                  type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 1
+                  type: double
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0	0.0
+10	10.0
+100	200.0
+103	206.0
+104	208.0
+105	105.0
+11	11.0
+111	111.0
+113	226.0
+114	114.0
+116	116.0
+118	236.0
+119	357.0
+12	24.0
+120	240.0
+125	250.0
+126	126.0
+128	384.0
+129	258.0
+131	131.0
+133	133.0
+134	268.0
+136	136.0
+137	274.0
+138	552.0
+143	143.0
+145	145.0
+146	292.0
+149	298.0
+15	30.0
+150	150.0
+152	304.0
+153	153.0
+155	155.0
+156	156.0
+157	157.0
+158	158.0
+160	160.0
+162	162.0
+163	163.0
+164	328.0
+165	330.0
+166	166.0
+167	501.0
+168	168.0
+169	676.0
+17	17.0
+170	170.0
+172	344.0
+174	348.0
+175	350.0
+176	352.0
+177	177.0
+178	178.0
+179	358.0
+18	36.0
+180	180.0
+181	181.0
+183	183.0
+186	186.0
+187	561.0
+189	189.0
+19	19.0
+190	190.0
+191	382.0
+192	192.0
+193	579.0
+194	194.0
+195	390.0
+196	196.0
+197	394.0
+199	597.0
+2	2.0
+20	20.0
+200	400.0
+201	201.0
+202	202.0
+203	406.0
+205	410.0
+207	414.0
+208	624.0
+209	418.0
+213	426.0
+214	214.0
+216	432.0
+217	434.0
+218	218.0
+219	438.0
+221	442.0
+222	222.0
+223	446.0
+224	448.0
+226	226.0
+228	228.0
+229	458.0
+230	1150.0
+233	466.0
+235	235.0
+237	474.0
+238	476.0
+239	478.0
+24	48.0
+241	241.0
+242	484.0
+244	244.0
+247	247.0
+248	248.0
+249	249.0
+252	252.0
+255	510.0
+256	512.0
+257	257.0
+258	258.0
+26	52.0
+260	260.0
+262	262.0
+263	263.0
+265	530.0
+266	266.0
+27	27.0
+272	544.0
+273	819.0
+274	274.0
+275	275.0
+277	1108.0
+278	556.0
+28	28.0
+280	560.0
+281	562.0
+282	564.0
+283	283.0
+284	284.0
+285	285.0
+286	286.0
+287	287.0
+288	576.0
+289	289.0
+291	291.0
+292	292.0
+296	296.0
+298	894.0
+30	30.0
+302	302.0
+305	305.0
+306	306.0
+307	614.0
+308	308.0
+309	618.0
+310	310.0
+311	933.0
+315	315.0
+316	948.0
+317	634.0
+318	954.0
+321	642.0
+322	644.0
+323	323.0
+325	650.0
+327	981.0
+33	33.0
+331	662.0
+332	332.0
+333	666.0
+335	335.0
+336	336.0
+338	338.0
+339	339.0
+34	34.0
+341	341.0
+342	684.0
+344	688.0
+345	345.0
+348	1740.0
+35	105.0
+351	351.0
+353	706.0
+356	356.0
+360	360.0
+362	362.0
+364	364.0
+365	365.0
+366	366.0
+367	734.0
+368	368.0
+369	1107.0
+37	74.0
+373	373.0
+374	374.0
+375	375.0
+377	377.0
+378	378.0
+379	379.0
+382	764.0
+384	1152.0
+386	386.0
+389	389.0
+392	392.0
+393	393.0
+394	394.0
+395	790.0
+396	1188.0
+397	794.0
+399	798.0
+4	4.0
+400	400.0
+401	2005.0
+402	402.0
+403	1209.0
+404	808.0
+406	1624.0
+407	407.0
+409	1227.0
+41	41.0
+411	411.0
+413	826.0
+414	828.0
+417	1251.0
+418	418.0
+419	419.0
+42	84.0
+421	421.0
+424	848.0
+427	427.0
+429	858.0
+43	43.0
+430	1290.0
+431	1293.0
+432	432.0
+435	435.0
+436	436.0
+437	437.0
+438	1314.0
+439	878.0
+44	44.0
+443	443.0
+444	444.0
+446	446.0
+448	448.0
+449	449.0
+452	452.0
+453	453.0
+454	1362.0
+455	455.0
+457	457.0
+458	916.0
+459	918.0
+460	460.0
+462	924.0
+463	926.0
+466	1398.0
+467	467.0
+468	1872.0
+469	2345.0
+47	47.0
+470	470.0
+472	472.0
+475	475.0
+477	477.0
+478	956.0
+479	479.0
+480	1440.0
+481	481.0
+482	482.0
+483	483.0
+484	484.0
+485	485.0
+487	487.0
+489	1956.0
+490	490.0
+491	491.0
+492	984.0
+493	493.0
+494	494.0
+495	495.0
+496	496.0
+497	497.0
+498	1494.0
+5	15.0
+51	102.0
+53	53.0
+54	54.0
+57	57.0
+58	116.0
+64	64.0
+65	65.0
+66	66.0
+67	134.0
+69	69.0
+70	210.0
+72	144.0
+74	74.0
+76	152.0
+77	77.0
+78	78.0
+8	8.0
+80	80.0
+82	82.0
+83	166.0
+84	168.0
+85	85.0
+86	86.0
+87	87.0
+9	9.0
+90	270.0
+92	92.0
+95	190.0
+96	96.0
+97	194.0
+98	196.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby1_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,367 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_g1)) (TOK_SELECT (TOK_SELEXPR (TOK_COLREF src key)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5)))) (TOK_GROUPBY (TOK_COLREF src key))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Reduce Output Operator
+              key expressions:
+                    expr: key
+                    type: string
+              sort order: +
+              Map-reduce partition columns:
+                    expr: key
+                    type: string
+              tag: -1
+              value expressions:
+                    expr: substr(value, 5)
+                    type: string
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(UDFToDouble(VALUE.0))
+          keys:
+                expr: KEY.0
+                type: string
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 1
+                  type: double
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest_g1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest_g1
+
+
+0	0.0
+10	10.0
+100	200.0
+103	206.0
+104	208.0
+105	105.0
+11	11.0
+111	111.0
+113	226.0
+114	114.0
+116	116.0
+118	236.0
+119	357.0
+12	24.0
+120	240.0
+125	250.0
+126	126.0
+128	384.0
+129	258.0
+131	131.0
+133	133.0
+134	268.0
+136	136.0
+137	274.0
+138	552.0
+143	143.0
+145	145.0
+146	292.0
+149	298.0
+15	30.0
+150	150.0
+152	304.0
+153	153.0
+155	155.0
+156	156.0
+157	157.0
+158	158.0
+160	160.0
+162	162.0
+163	163.0
+164	328.0
+165	330.0
+166	166.0
+167	501.0
+168	168.0
+169	676.0
+17	17.0
+170	170.0
+172	344.0
+174	348.0
+175	350.0
+176	352.0
+177	177.0
+178	178.0
+179	358.0
+18	36.0
+180	180.0
+181	181.0
+183	183.0
+186	186.0
+187	561.0
+189	189.0
+19	19.0
+190	190.0
+191	382.0
+192	192.0
+193	579.0
+194	194.0
+195	390.0
+196	196.0
+197	394.0
+199	597.0
+2	2.0
+20	20.0
+200	400.0
+201	201.0
+202	202.0
+203	406.0
+205	410.0
+207	414.0
+208	624.0
+209	418.0
+213	426.0
+214	214.0
+216	432.0
+217	434.0
+218	218.0
+219	438.0
+221	442.0
+222	222.0
+223	446.0
+224	448.0
+226	226.0
+228	228.0
+229	458.0
+230	1150.0
+233	466.0
+235	235.0
+237	474.0
+238	476.0
+239	478.0
+24	48.0
+241	241.0
+242	484.0
+244	244.0
+247	247.0
+248	248.0
+249	249.0
+252	252.0
+255	510.0
+256	512.0
+257	257.0
+258	258.0
+26	52.0
+260	260.0
+262	262.0
+263	263.0
+265	530.0
+266	266.0
+27	27.0
+272	544.0
+273	819.0
+274	274.0
+275	275.0
+277	1108.0
+278	556.0
+28	28.0
+280	560.0
+281	562.0
+282	564.0
+283	283.0
+284	284.0
+285	285.0
+286	286.0
+287	287.0
+288	576.0
+289	289.0
+291	291.0
+292	292.0
+296	296.0
+298	894.0
+30	30.0
+302	302.0
+305	305.0
+306	306.0
+307	614.0
+308	308.0
+309	618.0
+310	310.0
+311	933.0
+315	315.0
+316	948.0
+317	634.0
+318	954.0
+321	642.0
+322	644.0
+323	323.0
+325	650.0
+327	981.0
+33	33.0
+331	662.0
+332	332.0
+333	666.0
+335	335.0
+336	336.0
+338	338.0
+339	339.0
+34	34.0
+341	341.0
+342	684.0
+344	688.0
+345	345.0
+348	1740.0
+35	105.0
+351	351.0
+353	706.0
+356	356.0
+360	360.0
+362	362.0
+364	364.0
+365	365.0
+366	366.0
+367	734.0
+368	368.0
+369	1107.0
+37	74.0
+373	373.0
+374	374.0
+375	375.0
+377	377.0
+378	378.0
+379	379.0
+382	764.0
+384	1152.0
+386	386.0
+389	389.0
+392	392.0
+393	393.0
+394	394.0
+395	790.0
+396	1188.0
+397	794.0
+399	798.0
+4	4.0
+400	400.0
+401	2005.0
+402	402.0
+403	1209.0
+404	808.0
+406	1624.0
+407	407.0
+409	1227.0
+41	41.0
+411	411.0
+413	826.0
+414	828.0
+417	1251.0
+418	418.0
+419	419.0
+42	84.0
+421	421.0
+424	848.0
+427	427.0
+429	858.0
+43	43.0
+430	1290.0
+431	1293.0
+432	432.0
+435	435.0
+436	436.0
+437	437.0
+438	1314.0
+439	878.0
+44	44.0
+443	443.0
+444	444.0
+446	446.0
+448	448.0
+449	449.0
+452	452.0
+453	453.0
+454	1362.0
+455	455.0
+457	457.0
+458	916.0
+459	918.0
+460	460.0
+462	924.0
+463	926.0
+466	1398.0
+467	467.0
+468	1872.0
+469	2345.0
+47	47.0
+470	470.0
+472	472.0
+475	475.0
+477	477.0
+478	956.0
+479	479.0
+480	1440.0
+481	481.0
+482	482.0
+483	483.0
+484	484.0
+485	485.0
+487	487.0
+489	1956.0
+490	490.0
+491	491.0
+492	984.0
+493	493.0
+494	494.0
+495	495.0
+496	496.0
+497	497.0
+498	1494.0
+5	15.0
+51	102.0
+53	53.0
+54	54.0
+57	57.0
+58	116.0
+64	64.0
+65	65.0
+66	66.0
+67	134.0
+69	69.0
+70	210.0
+72	144.0
+74	74.0
+76	152.0
+77	77.0
+78	78.0
+8	8.0
+80	80.0
+82	82.0
+83	166.0
+84	168.0
+85	85.0
+86	86.0
+87	87.0
+9	9.0
+90	270.0
+92	92.0
+95	190.0
+96	96.0
+97	194.0
+98	196.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,123 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (TOK_COLREF src key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5))))) (TOK_GROUPBY (TOK_FUNCTION substr (TOK_COLREF src key) 1 1))))
+
+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
+      Alias -> Map Operator Tree:
+        src 
+            Group By Operator
+              aggregations:
+                    expr: sum(UDFToDouble(substr(value, 5)))
+                    expr: count(DISTINCT substr(value, 5))
+              keys:
+                    expr: substr(key, 1, 1)
+                    type: string
+                    expr: substr(value, 5)
+                    type: string
+              mode: hash
+              Reduce Output Operator
+                key expressions:
+                      expr: 0
+                      type: string
+                      expr: 1
+                      type: string
+                sort order: ++
+                Map-reduce partition columns:
+                      expr: 0
+                      type: string
+                      expr: 1
+                      type: string
+                tag: -1
+                value expressions:
+                      expr: 2
+                      type: double
+                      expr: 3
+                      type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+                expr: count(DISTINCT KEY.1)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: partial2
+          File Output Operator
+            compressed: false
+            GlobalTableId: 0
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.mapred.SequenceFileOutputFormat
+                name: binary_table
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        /data/users/njain/hive1/hive/build/ql/tmp/75626022/245324029.10001 
+          Reduce Output Operator
+            key expressions:
+                  expr: 0
+                  type: string
+            sort order: +
+            Map-reduce partition columns:
+                  expr: 0
+                  type: string
+            tag: -1
+            value expressions:
+                  expr: 1
+                  type: double
+                  expr: 2
+                  type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+                expr: count(VALUE.1)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 2
+                  type: bigint
+                  expr: concat(0, UDFToString(1))
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0	1	00.0
+1	71	116414.0
+2	69	225571.0
+3	62	332004.0
+4	74	452763.0
+5	6	5397.0
+6	5	6398.0
+7	6	7735.0
+8	8	8762.0
+9	7	91047.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,70 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_g2)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (TOK_COLREF src key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5))))) (TOK_GROUPBY (TOK_FUNCTION substr (TOK_COLREF src key) 1 1))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Reduce Output Operator
+              key expressions:
+                    expr: substr(key, 1, 1)
+                    type: string
+                    expr: substr(value, 5)
+                    type: string
+              sort order: ++
+              Map-reduce partition columns:
+                    expr: substr(key, 1, 1)
+                    type: string
+              tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(UDFToDouble(KEY.1))
+                expr: count(DISTINCT KEY.1)
+          keys:
+                expr: KEY.0
+                type: string
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 2
+                  type: bigint
+                  expr: concat(0, UDFToString(1))
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest_g2
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest_g2
+
+
+0	1	00.0
+1	71	116414.0
+2	69	225571.0
+3	62	332004.0
+4	74	452763.0
+5	6	5397.0
+6	5	6398.0
+7	6	7735.0
+8	8	8762.0
+9	7	91047.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,125 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION avg (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI avg (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_FUNCTION substr (TOK_COLREF src value) 5))))))
+
+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
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              Group By Operator
+                aggregations:
+                      expr: sum(UDFToDouble(substr(0, 5)))
+                      expr: max(substr(0, 5))
+                      expr: avg(DISTINCT UDFToDouble(substr(0, 5)))
+                      expr: min(substr(0, 5))
+                      expr: avg(UDFToDouble(substr(0, 5)))
+                keys:
+                      expr: substr(0, 5)
+                      type: string
+                mode: hash
+                Reduce Output Operator
+                  key expressions:
+                        expr: 0
+                        type: string
+                  sort order: +
+                  Map-reduce partition columns:
+                        expr: 0
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: 1
+                        type: double
+                        expr: 2
+                        type: string
+                        expr: 3
+                        type: string
+                        expr: 4
+                        type: string
+                        expr: 5
+                        type: string
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+                expr: max(VALUE.1)
+                expr: avg(DISTINCT UDFToDouble(KEY.0))
+                expr: min(VALUE.3)
+                expr: avg(VALUE.4)
+          mode: partial2
+          File Output Operator
+            compressed: false
+            GlobalTableId: 0
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.mapred.SequenceFileOutputFormat
+                name: binary_table
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        /data/users/njain/hive1/hive/build/ql/tmp/60912787/134510876.10001 
+          Reduce Output Operator
+            sort order: 
+            tag: -1
+            value expressions:
+                  expr: 0
+                  type: double
+                  expr: 1
+                  type: string
+                  expr: 2
+                  type: string
+                  expr: 3
+                  type: string
+                  expr: 4
+                  type: string
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+                expr: max(VALUE.1)
+                expr: avg(VALUE.2)
+                expr: min(VALUE.3)
+                expr: avg(VALUE.4)
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: double
+                  expr: 4
+                  type: double
+                  expr: 2
+                  type: double
+                  expr: 1
+                  type: string
+                  expr: 3
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+130091.0	260.182	256.10355987055016	98.0	0.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,64 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION avg (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI avg (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_FUNCTION substr (TOK_COLREF src value) 5))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_FUNCTION substr (TOK_COLREF src value) 5))))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              Reduce Output Operator
+                key expressions:
+                      expr: substr(0, 5)
+                      type: string
+                sort order: +
+                tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(UDFToDouble(KEY.0))
+                expr: max(KEY.0)
+                expr: avg(DISTINCT UDFToDouble(KEY.0))
+                expr: min(KEY.0)
+                expr: avg(UDFToDouble(KEY.0))
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: double
+                  expr: 4
+                  type: double
+                  expr: 2
+                  type: double
+                  expr: 1
+                  type: string
+                  expr: 3
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+130091.0	260.182	256.10355987055016	98.0	0.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,53 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              Group By Operator
+                aggregations:
+                      expr: count(1)
+                mode: hash
+                Reduce Output Operator
+                  sort order: 
+                  tag: -1
+                  value expressions:
+                        expr: 0
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE.0)
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: bigint
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+500

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby4_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,65 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src key) 1 1))) (TOK_GROUPBY (TOK_FUNCTION substr (TOK_COLREF src key) 1 1))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: key
+                    type: string
+              Reduce Output Operator
+                key expressions:
+                      expr: substr(0, 1, 1)
+                      type: string
+                sort order: +
+                Map-reduce partition columns:
+                      expr: substr(0, 1, 1)
+                      type: string
+                tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          keys:
+                expr: KEY.0
+                type: string
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,56 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_COLREF src key))))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: key
+                    type: string
+              Group By Operator
+                aggregations:
+                      expr: sum(UDFToDouble(0))
+                mode: hash
+                Reduce Output Operator
+                  sort order: 
+                  tag: -1
+                  value expressions:
+                        expr: 0
+                        type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE.0)
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: double
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+NULL

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby5_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,367 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_COLREF src key)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (TOK_COLREF src value) 5)))) (TOK_GROUPBY (TOK_COLREF src key))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Reduce Output Operator
+              key expressions:
+                    expr: key
+                    type: string
+              sort order: +
+              Map-reduce partition columns:
+                    expr: key
+                    type: string
+              tag: -1
+              value expressions:
+                    expr: substr(value, 5)
+                    type: string
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(UDFToDouble(VALUE.0))
+          keys:
+                expr: KEY.0
+                type: string
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+                  expr: 1
+                  type: double
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0	0.0
+10	10.0
+100	200.0
+103	206.0
+104	208.0
+105	105.0
+11	11.0
+111	111.0
+113	226.0
+114	114.0
+116	116.0
+118	236.0
+119	357.0
+12	24.0
+120	240.0
+125	250.0
+126	126.0
+128	384.0
+129	258.0
+131	131.0
+133	133.0
+134	268.0
+136	136.0
+137	274.0
+138	552.0
+143	143.0
+145	145.0
+146	292.0
+149	298.0
+15	30.0
+150	150.0
+152	304.0
+153	153.0
+155	155.0
+156	156.0
+157	157.0
+158	158.0
+160	160.0
+162	162.0
+163	163.0
+164	328.0
+165	330.0
+166	166.0
+167	501.0
+168	168.0
+169	676.0
+17	17.0
+170	170.0
+172	344.0
+174	348.0
+175	350.0
+176	352.0
+177	177.0
+178	178.0
+179	358.0
+18	36.0
+180	180.0
+181	181.0
+183	183.0
+186	186.0
+187	561.0
+189	189.0
+19	19.0
+190	190.0
+191	382.0
+192	192.0
+193	579.0
+194	194.0
+195	390.0
+196	196.0
+197	394.0
+199	597.0
+2	2.0
+20	20.0
+200	400.0
+201	201.0
+202	202.0
+203	406.0
+205	410.0
+207	414.0
+208	624.0
+209	418.0
+213	426.0
+214	214.0
+216	432.0
+217	434.0
+218	218.0
+219	438.0
+221	442.0
+222	222.0
+223	446.0
+224	448.0
+226	226.0
+228	228.0
+229	458.0
+230	1150.0
+233	466.0
+235	235.0
+237	474.0
+238	476.0
+239	478.0
+24	48.0
+241	241.0
+242	484.0
+244	244.0
+247	247.0
+248	248.0
+249	249.0
+252	252.0
+255	510.0
+256	512.0
+257	257.0
+258	258.0
+26	52.0
+260	260.0
+262	262.0
+263	263.0
+265	530.0
+266	266.0
+27	27.0
+272	544.0
+273	819.0
+274	274.0
+275	275.0
+277	1108.0
+278	556.0
+28	28.0
+280	560.0
+281	562.0
+282	564.0
+283	283.0
+284	284.0
+285	285.0
+286	286.0
+287	287.0
+288	576.0
+289	289.0
+291	291.0
+292	292.0
+296	296.0
+298	894.0
+30	30.0
+302	302.0
+305	305.0
+306	306.0
+307	614.0
+308	308.0
+309	618.0
+310	310.0
+311	933.0
+315	315.0
+316	948.0
+317	634.0
+318	954.0
+321	642.0
+322	644.0
+323	323.0
+325	650.0
+327	981.0
+33	33.0
+331	662.0
+332	332.0
+333	666.0
+335	335.0
+336	336.0
+338	338.0
+339	339.0
+34	34.0
+341	341.0
+342	684.0
+344	688.0
+345	345.0
+348	1740.0
+35	105.0
+351	351.0
+353	706.0
+356	356.0
+360	360.0
+362	362.0
+364	364.0
+365	365.0
+366	366.0
+367	734.0
+368	368.0
+369	1107.0
+37	74.0
+373	373.0
+374	374.0
+375	375.0
+377	377.0
+378	378.0
+379	379.0
+382	764.0
+384	1152.0
+386	386.0
+389	389.0
+392	392.0
+393	393.0
+394	394.0
+395	790.0
+396	1188.0
+397	794.0
+399	798.0
+4	4.0
+400	400.0
+401	2005.0
+402	402.0
+403	1209.0
+404	808.0
+406	1624.0
+407	407.0
+409	1227.0
+41	41.0
+411	411.0
+413	826.0
+414	828.0
+417	1251.0
+418	418.0
+419	419.0
+42	84.0
+421	421.0
+424	848.0
+427	427.0
+429	858.0
+43	43.0
+430	1290.0
+431	1293.0
+432	432.0
+435	435.0
+436	436.0
+437	437.0
+438	1314.0
+439	878.0
+44	44.0
+443	443.0
+444	444.0
+446	446.0
+448	448.0
+449	449.0
+452	452.0
+453	453.0
+454	1362.0
+455	455.0
+457	457.0
+458	916.0
+459	918.0
+460	460.0
+462	924.0
+463	926.0
+466	1398.0
+467	467.0
+468	1872.0
+469	2345.0
+47	47.0
+470	470.0
+472	472.0
+475	475.0
+477	477.0
+478	956.0
+479	479.0
+480	1440.0
+481	481.0
+482	482.0
+483	483.0
+484	484.0
+485	485.0
+487	487.0
+489	1956.0
+490	490.0
+491	491.0
+492	984.0
+493	493.0
+494	494.0
+495	495.0
+496	496.0
+497	497.0
+498	1494.0
+5	15.0
+51	102.0
+53	53.0
+54	54.0
+57	57.0
+58	116.0
+64	64.0
+65	65.0
+66	66.0
+67	134.0
+69	69.0
+70	210.0
+72	144.0
+74	74.0
+76	152.0
+77	77.0
+78	78.0
+8	8.0
+80	80.0
+82	82.0
+83	166.0
+84	168.0
+85	85.0
+86	86.0
+87	87.0
+9	9.0
+90	270.0
+92	92.0
+95	190.0
+96	96.0
+97	194.0
+98	196.0

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,70 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECTDI (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src value) 5 1)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              Group By Operator
+                keys:
+                      expr: substr(0, 5, 1)
+                      type: string
+                mode: hash
+                Reduce Output Operator
+                  key expressions:
+                        expr: 0
+                        type: string
+                  sort order: +
+                  Map-reduce partition columns:
+                        expr: 0
+                        type: string
+                  tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          keys:
+                expr: KEY.0
+                type: string
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map_skew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map_skew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_map_skew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,98 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECTDI (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src value) 5 1)))))
+
+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
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              Group By Operator
+                keys:
+                      expr: substr(0, 5, 1)
+                      type: string
+                mode: hash
+                Reduce Output Operator
+                  key expressions:
+                        expr: 0
+                        type: string
+                  sort order: +
+                  Map-reduce partition columns:
+                        expr: rand()
+                        type: double
+                  tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          keys:
+                expr: KEY.0
+                type: string
+          mode: partial2
+          File Output Operator
+            compressed: false
+            GlobalTableId: 0
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.mapred.SequenceFileOutputFormat
+                name: binary_table
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        /data/users/njain/hive1/hive/build/ql/tmp/25440580/85551756.10001 
+          Reduce Output Operator
+            key expressions:
+                  expr: 0
+                  type: string
+            sort order: +
+            Map-reduce partition columns:
+                  expr: 0
+                  type: string
+            tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          keys:
+                expr: KEY.0
+                type: string
+          mode: final
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9

Added: hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_noskew.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_noskew.q.out?rev=752034&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_noskew.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/groupby6_noskew.q.out Tue Mar 10 10:23:40 2009
@@ -0,0 +1,65 @@
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECTDI (TOK_SELEXPR (TOK_FUNCTION substr (TOK_COLREF src value) 5 1)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              Reduce Output Operator
+                key expressions:
+                      expr: substr(0, 5, 1)
+                      type: string
+                sort order: +
+                Map-reduce partition columns:
+                      expr: substr(0, 5, 1)
+                      type: string
+                tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          keys:
+                expr: KEY.0
+                type: string
+          mode: complete
+          Select Operator
+            expressions:
+                  expr: 0
+                  type: string
+            File Output Operator
+              compressed: false
+              GlobalTableId: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+            replace: true
+            table:
+                input format: org.apache.hadoop.mapred.TextInputFormat
+                output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                name: dest1
+
+
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9



Mime
View raw message