hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jcama...@apache.org
Subject [02/10] hive git commit: HIVE-17286: Avoid expensive String serialization/deserialization for bitvectors (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Date Thu, 17 Aug 2017 22:42:26 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/9a36aa90/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
index d51a544..6b6ba4d 100644
--- a/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
+++ b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
@@ -115,8 +115,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	3                   	0.75                	2                   	          
         	                    	SExM4AMDgaTbFcD8mOYCwMOJoQQ=	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	3                   	0.75                	2                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') state
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -125,8 +124,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	6                   	3.0                 	3                   	          
         	                    	SExM4AYGhJ2RPL68foHA90C/kJJjgJX39QKAwfg7	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	6                   	3.0                 	3                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -135,8 +133,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	double              	1.0                 	4.0                 	0   
               	4                   	                    	                    	          
         	                    	SExM4AQEwvmagwOC4fQQ/cXBowKCnueKAg==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	double              	1.0                 	4.0                 	0   
               	4                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -145,8 +142,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	double              	1.0                 	5.0                 	0   
               	5                   	                    	                    	          
         	                    	SExM4AUFgoqWCcDvhPoCguH0EP3FwaMCgp7nigI=	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	double              	1.0                 	5.0                 	0   
               	5                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -155,8 +151,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	10                  	2000                	0   
               	4                   	                    	                    	          
         	                    	SExM4AQEwtKH1wOJpIYp95+qNYHs8ZgB	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	10                  	2000                	0   
               	4                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -165,8 +160,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	10                  	910                 	0   
               	4                   	                    	                    	          
         	                    	SExM4AQEwavm2wOC18PyAYDUhBSCqe9l	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	10                  	910                 	0   
               	4                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') zip
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -175,8 +169,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	SExM4AMDgaPxmgPB562MAr/LtnY=	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') zip
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -185,8 +178,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	SExM4AMDgaPxmgPB562MAr/LtnY=	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d
 PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d
@@ -424,8 +416,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	2                   	0.5                 	1                   	          
         	                    	SExM4AICgaTbFYDJnvoC	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	2                   	0.5                 	1                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') state
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -434,8 +425,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	3                   	1.25                	4                   	          
         	                    	SExM4AMDgaTbFcD8mOYCwJDuDA==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	3                   	1.25                	4                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -444,8 +434,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	double              	1.0                 	2.0                 	0   
               	2                   	                    	                    	          
         	                    	SExM4AICwvmagwP/pra0Ag==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	double              	1.0                 	2.0                 	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -454,8 +443,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	double              	1.0                 	31.0                	0   
               	5                   	                    	                    	          
         	                    	SExM4AUFgoqWCb/8tKEBg9TE6QH9xcGjAoKe54oC	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	double              	1.0                 	31.0                	0   
               	5                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -464,8 +452,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	1000                	1010                	0   
               	2                   	                    	                    	          
         	                    	SExM4AICwtKH1wOJpIYp	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	1000                	1010                	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -474,8 +461,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	1000                	2000                	0   
               	3                   	                    	                    	          
         	                    	SExM4AMDwtKH1wOJpIYp95+qNQ==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	1000                	2000                	0   
               	3                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') zip
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -484,8 +470,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-zip                 	int                 	94086               	94087               	0   
               	2                   	                    	                    	          
         	                    	SExM4AICgaPxmgOAs+SCAw==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+zip                 	int                 	94086               	94087               	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') zip
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_1d
@@ -494,8 +479,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_1d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	SExM4AMDgaPxmgPB562MAr/LtnY=	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+zip                 	int                 	43201               	94087               	0   
               	3                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d
 PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d
@@ -804,8 +788,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	2                   	0.5                 	1                   	          
         	                    	SExM4AICgaTbFYDAoocH	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	2                   	0.5                 	1                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') state
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_2d
@@ -814,8 +797,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-state               	string              	                    	                    	0   
               	3                   	3.0                 	3                   	          
         	                    	SExM4AMDwtmPPYHA90C/kJJj	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+state               	string              	                    	                    	0   
               	3                   	3.0                 	3                   	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_2d
@@ -824,8 +806,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	int                 	2                   	3                   	0   
               	2                   	                    	                    	          
         	                    	SExM4AICga/rqgHA0vSOAw==	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	int                 	2                   	3                   	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') locid
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_2d
@@ -834,8 +815,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-locid               	int                 	1                   	5                   	0   
               	3                   	                    	                    	          
         	                    	SExM4AMDxfO+SLy7rGLA9IJO	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+locid               	int                 	1                   	5                   	0   
               	3                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_2d
@@ -844,8 +824,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	1000                	2000                	0   
               	2                   	                    	                    	          
         	                    	SExM4AICy/aNgAT3n6o1	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	1000                	2000                	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') cnt
 PREHOOK: type: DESCTABLE
 PREHOOK: Input: default@loc_orc_2d
@@ -854,8 +833,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@loc_orc_2d
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-cnt                 	decimal(10,0)       	10                  	100                 	0   
               	2                   	                    	                    	          
         	                    	SExM4AICw4KqzgWC/fN5	 
-	from deserializer   	 	 	 	 	 	 	 	 	 	 
+cnt                 	decimal(10,0)       	10                  	100                 	0   
               	2                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_2d
 PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_2d

http://git-wip-us.apache.org/repos/asf/hive/blob/9a36aa90/ql/src/test/results/clientpositive/llap/llap_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_stats.q.out b/ql/src/test/results/clientpositive/llap/llap_stats.q.out
index fda614f..0f32be2 100644
--- a/ql/src/test/results/clientpositive/llap/llap_stats.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_stats.q.out
@@ -118,13 +118,13 @@ STAGE PLANS:
                       keys: cint (type: int)
                       mode: hash
                       outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 5 Data size: 4660 Basic stats: COMPLETE Column
stats: PARTIAL
+                      Statistics: Num rows: 5 Data size: 4260 Basic stats: COMPLETE Column
stats: PARTIAL
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 5 Data size: 4660 Basic stats: COMPLETE Column
stats: PARTIAL
-                        value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>),
_col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>)
+                        Statistics: Num rows: 5 Data size: 4260 Basic stats: COMPLETE Column
stats: PARTIAL
+                        value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>),
_col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
             Execution mode: llap
             LLAP IO: all inputs
         Reducer 2 
@@ -135,14 +135,14 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 5 Data size: 4820 Basic stats: COMPLETE Column stats:
PARTIAL
+                Statistics: Num rows: 5 Data size: 4420 Basic stats: COMPLETE Column stats:
PARTIAL
                 Select Operator
-                  expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:string>),
_col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:string>),
_col0 (type: int)
+                  expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>),
_col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>),
_col0 (type: int)
                   outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 5 Data size: 4820 Basic stats: COMPLETE Column stats:
PARTIAL
+                  Statistics: Num rows: 5 Data size: 4420 Basic stats: COMPLETE Column stats:
PARTIAL
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 5 Data size: 4820 Basic stats: COMPLETE Column
stats: PARTIAL
+                    Statistics: Num rows: 5 Data size: 4420 Basic stats: COMPLETE Column
stats: PARTIAL
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/9a36aa90/ql/src/test/results/clientpositive/llap/parallel_colstats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/parallel_colstats.q.out b/ql/src/test/results/clientpositive/llap/parallel_colstats.q.out
index 57498a6..e89bf2f 100644
--- a/ql/src/test/results/clientpositive/llap/parallel_colstats.q.out
+++ b/ql/src/test/results/clientpositive/llap/parallel_colstats.q.out
@@ -105,11 +105,11 @@ STAGE PLANS:
                       aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column
stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column
stats: COMPLETE
-                        value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
+                        Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column
stats: COMPLETE
+                        value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
                 Group By Operator
                   keys: KEY._col0 (type: string), KEY._col1 (type: string)
                   mode: complete
@@ -131,11 +131,11 @@ STAGE PLANS:
                       aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column
stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column
stats: COMPLETE
-                        value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
+                        Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column
stats: COMPLETE
+                        value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
         Reducer 4 
             Execution mode: llap
             Reduce Operator Tree:
@@ -143,10 +143,10 @@ STAGE PLANS:
                 aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats:
COMPLETE
+                Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats:
COMPLETE
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -158,10 +158,10 @@ STAGE PLANS:
                 aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats:
COMPLETE
+                Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats:
COMPLETE
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/9a36aa90/ql/src/test/results/clientpositive/llap/stats_only_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out
index ab91ea7..ed87791 100644
--- a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out
+++ b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out
@@ -415,8 +415,7 @@ POSTHOOK: type: DESCTABLE
 POSTHOOK: Input: default@stats_null_part
 # col_name            	data_type           	min                 	max                 	num_nulls
          	distinct_count      	avg_col_len         	max_col_len         	num_trues      
    	num_falses          	comment             	bitVector           
 	 	 	 	 	 	 	 	 	 	 	 
-a                   	double              	1.0                 	1.0                 	1   
               	1                   	                    	                    	          
         	                    	SExM4AEBwaDRtwU=	 
-  	from deserializer   	 	 	 	 	 	 	 	 	 	 
+a                   	double              	1.0                 	1.0                 	1   
               	1                   	                    	                    	          
         	                    	HL                  	from deserializer   
 PREHOOK: query: drop table stats_null
 PREHOOK: type: DROPTABLE
 PREHOOK: Input: default@stats_null

http://git-wip-us.apache.org/repos/asf/hive/blob/9a36aa90/ql/src/test/results/clientpositive/llap/varchar_udf1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/varchar_udf1.q.out b/ql/src/test/results/clientpositive/llap/varchar_udf1.q.out
index 023d51c..fe20d54 100644
--- a/ql/src/test/results/clientpositive/llap/varchar_udf1.q.out
+++ b/ql/src/test/results/clientpositive/llap/varchar_udf1.q.out
@@ -406,7 +406,7 @@ from varchar_udf_1
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@varchar_udf_1
 #### A masked pattern was here ####
-{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"Rk0QAAEAAAAIAAAABAAAAAgAAAACAAAAAQAAAAQAAAABAAAAAgAAAAEAAAABAAAAAgAAAAgAAAAE\r\nAAAAAQAAAAgAAAA=\r\n"}
{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"Rk0QAAEAAAAIAAAABAAAAAgAAAACAAAAAQAAAAQAAAABAAAAAgAAAAEAAAABAAAAAgAAAAgAAAAE\r\nAAAAAQAAAAgAAAA=\r\n"}
+{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM
Mime
View raw message