http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/cbo_rp_lineage2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/cbo_rp_lineage2.q.out b/ql/src/test/results/clientpositive/llap/cbo_rp_lineage2.q.out index 44f9d68..ed63ddd 100644 --- a/ql/src/test/results/clientpositive/llap/cbo_rp_lineage2.q.out +++ b/ql/src/test/results/clientpositive/llap/cbo_rp_lineage2.q.out @@ -36,7 +36,7 @@ PREHOOK: query: insert into table dest1 select * from src2 PREHOOK: type: QUERY PREHOOK: Input: default@src2 PREHOOK: Output: default@dest1 -{"version":"1.0","engine":"tez","database":"default","hash":"ecc718a966d8887b18084a55dd96f0bc","queryText":"insert into table dest1 select * from src2","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"ecc718a966d8887b18084a55dd96f0bc","queryText":"insert into table dest1 select * from src2","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: select key k, dest1.value from dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -467,20 +467,20 @@ PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"tez","database":"default","hash":"e494b771d94800dc3430bf5d0810cd9f","queryText":"insert overwrite table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[],"vertices":[]} +{"version":"1.0","engine":"tez","database":"default","hash":"e494b771d94800dc3430bf5d0810cd9f","queryText":"insert overwrite table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"src2.key2 is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2. key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: insert into table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"tez","database":"default","hash":"efeaddd0d36105b1013b414627850dc2","queryText":"insert into table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[],"vertices":[]} +{"version":"1.0","engine":"tez","database":"default","hash":"efeaddd0d36105b1013b414627850dc2","queryText":"insert into table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"src2.key2 is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"} ,{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: insert into table dest2 select * from src1 JOIN src2 ON length(src1.value) = length(src2.value2) + 1 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"tez","database":"default","hash":"e9450a56b3d103642e06bef0e4f0d482","queryText":"insert into table dest2\n select * from src1 JOIN src2 ON length(src1.value) = length(src2.value2) + 1","edges":[],"vertices":[]} +{"version":"1.0","engine":"tez","database":"default","hash":"e9450a56b3d103642e06bef0e4f0d482","queryText":"insert into table dest2\n select * from src1 JOIN src2 ON length(src1.value) = length(src2.value2) + 1","edges":[{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3],"expression":"length(src1.value) is not null","edgeType":"PREDICATE"},{"sources":[5,7],"targets":[0,1,2,3],"expression":"(length(src1.value) = (length(src2.value2) + 1))","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2,3],"expression":"length(src2.value2) is not null","edgeType":"PREDICATE"}], "vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: select * from src1 where length(key) > 2 PREHOOK: type: QUERY PREHOOK: Input: default@src1 @@ -530,7 +530,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"tez","database":"default","hash":"76d84512204ddc576ad4d93f252e4358","queryText":"insert overwrite table dest2\n select * from src1 JOIN src2 ON src1.key = src2.key2 WHERE length(key) > 3","edges":[],"vertices":[]} +{"version":"1.0","engine":"tez","database":"default","hash":"76d84512204ddc576ad4d93f252e4358","queryText":"insert overwrite table dest2\n select * from src1 JOIN src2 ON src1.key = src2.key2 WHERE length(key) > 3","edges":[{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"((length(src1.key) > 3) and src1.key is not null)","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"((length(src2.key2) > 3) and src2.key2 is not null)","edgeType ":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: drop table if exists dest_l1 PREHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE dest_l1(key INT, value STRING) STORED AS TEXTFILE @@ -552,7 +552,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Output: default@dest_l1 -{"version":"1.0","engine":"tez","database":"default","hash":"60b589744e2527dd235a6c8168d6a653","queryText":"INSERT OVERWRITE TABLE dest_l1\nSELECT j.*\nFROM (SELECT t1.key, p1.value\n FROM src1 t1\n LEFT OUTER JOIN src p1\n ON (t1.key = p1.key)\n UNION ALL\n SELECT t2.key, p2.value\n FROM src1 t2\n LEFT OUTER JOIN src p2\n ON (t2.key = p2.key)) j","edges":[{"sources":[2],"targets":[0],"expression":"UDFToInteger(key)","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"value","edgeType":"PROJECTION"},{"sources":[4,2],"targets":[0,1],"expression":"(j-subquery1:_u1-subquery1:p1.key = j-subquery1:_u1-subquery1:t1.key)","edgeType":"PREDICATE"},{"sources":[4,2],"targets":[0,1],"expression":"(j-subquery2:_u1-subquery2:p2.key = j-subquery2:_u1-subquery2:t2.key)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_l1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l1.value"},{"id":2," vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src.key"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"60b589744e2527dd235a6c8168d6a653","queryText":"INSERT OVERWRITE TABLE dest_l1\nSELECT j.*\nFROM (SELECT t1.key, p1.value\n FROM src1 t1\n LEFT OUTER JOIN src p1\n ON (t1.key = p1.key)\n UNION ALL\n SELECT t2.key, p2.value\n FROM src1 t2\n LEFT OUTER JOIN src p2\n ON (t2.key = p2.key)) j","edges":[{"sources":[2],"targets":[0],"expression":"UDFToInteger(key)","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"value","edgeType":"PROJECTION"},{"sources":[4,2],"targets":[0,1],"expression":"(j-subquery1:_u1-subquery1:p1.key = j-subquery1:_u1-subquery1:t1.key)","edgeType":"PREDICATE"},{"sources":[4,2],"targets":[0,1],"expression":"(j-subquery2:_u1-subquery2:p2.key = j-subquery2:_u1-subquery2:t2.key)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0],"expression":"compute_stats(UDFToInteger(key), 'hll')","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":" compute_stats(value, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_l1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src.key"}]} PREHOOK: query: drop table if exists emp PREHOOK: type: DROPTABLE PREHOOK: query: drop table if exists dept @@ -593,7 +593,7 @@ PREHOOK: Input: default@dept PREHOOK: Input: default@emp PREHOOK: Input: default@project PREHOOK: Output: default@tgt -{"version":"1.0","engine":"tez","database":"default","hash":"f59797e0422d2e51515063374dfac361","queryText":"INSERT INTO TABLE tgt\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept d ON d.dept_id = em.dept_id\n ) emd JOIN project p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id is not null and e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.emp _id = emd:em:m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12,9],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.dept_id = emd:d.dept_id AND emd:em:e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept.dept_name"},{"id":7,"vertexType":"COLUMN ","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept.dept_id"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"f59797e0422d2e51515063374dfac361","queryText":"INSERT INTO TABLE tgt\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept d ON d.dept_id = em.dept_id\n ) emd JOIN project p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id is not null and e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.emp _id = emd:em:m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12,9],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.dept_id = emd:d.dept_id AND emd:em:e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"},{"sources":[6],"targets":[0],"expression":"compute_stats(default.dept.dept_name, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"expression":"compute_stats(default.emp.name, 'hll')","edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"expression":"compute_stats(default.emp.emp_id, 'hll')","edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"expression":"compute_stats(default.project.project_id, 'hll')","edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"expressi on":"compute_stats(default.project.project_name, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept.dept_name"},{"id":7,"vertexType":"COLUMN","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept.dept_id"}]} PREHOOK: query: drop table if exists dest_l2 PREHOOK: type: DROPTABLE PREHOOK: query: create table dest_l2 (id int, c1 tinyint, c2 int, c3 bigint) stored as textfile @@ -603,7 +603,7 @@ PREHOOK: Output: default@dest_l2 PREHOOK: query: insert into dest_l2 values(0, 1, 100, 10000) PREHOOK: type: QUERY PREHOOK: Output: default@dest_l2 -{"version":"1.0","engine":"tez","database":"default","hash":"e001334e3f8384806b0f25a7c303045f","queryText":"insert into dest_l2 values(0, 1, 100, 10000)","edges":[{"sources":[],"targets":[0],"expression":"UDFToInteger(tmp_values_col1)","edgeType":"PROJECTION"},{"sources":[],"targets":[1],"expression":"UDFToByte(tmp_values_col2)","edgeType":"PROJECTION"},{"sources":[],"targets":[2],"expression":"UDFToInteger(tmp_values_col3)","edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"UDFToLong(tmp_values_col4)","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l2.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.c3"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"e001334e3f8384806b0f25a7c303045f","queryText":"insert into dest_l2 values(0, 1, 100, 10000)","edges":[{"sources":[],"targets":[0],"expression":"UDFToInteger(tmp_values_col1)","edgeType":"PROJECTION"},{"sources":[],"targets":[1],"expression":"UDFToByte(tmp_values_col2)","edgeType":"PROJECTION"},{"sources":[],"targets":[2],"expression":"UDFToInteger(tmp_values_col3)","edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"UDFToLong(tmp_values_col4)","edgeType":"PROJECTION"},{"sources":[],"targets":[0],"expression":"compute_stats(UDFToInteger(tmp_values_col1), 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[1],"expression":"compute_stats(UDFToByte(tmp_values_col2), 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[2],"expression":"compute_stats(UDFToInteger(tmp_values_col3), 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"compute_stats(UDFToLong(tmp_values_col4), 'hll')" ,"edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l2.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.c3"}]} PREHOOK: query: select * from ( select c1 + c2 x from dest_l2 union all @@ -623,7 +623,7 @@ PREHOOK: Output: default@dest_l3 PREHOOK: query: insert into dest_l3 values(0, "s1", "s2", 15) PREHOOK: type: QUERY PREHOOK: Output: default@dest_l3 -{"version":"1.0","engine":"tez","database":"default","hash":"09df51ba6ba2d07f2304523ee505f094","queryText":"insert into dest_l3 values(0, \"s1\", \"s2\", 15)","edges":[{"sources":[],"targets":[0],"expression":"UDFToInteger(tmp_values_col1)","edgeType":"PROJECTION"},{"sources":[],"targets":[1,2],"edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"UDFToInteger(tmp_values_col4)","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_l3.id"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l3.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l3.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l3.c3"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"09df51ba6ba2d07f2304523ee505f094","queryText":"insert into dest_l3 values(0, \"s1\", \"s2\", 15)","edges":[{"sources":[],"targets":[0],"expression":"UDFToInteger(tmp_values_col1)","edgeType":"PROJECTION"},{"sources":[],"targets":[1,2],"edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"UDFToInteger(tmp_values_col4)","edgeType":"PROJECTION"},{"sources":[],"targets":[0],"expression":"compute_stats(UDFToInteger(tmp_values_col1), 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[1],"expression":"compute_stats(default.values__tmp__table__2.tmp_values_col2, 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[2],"expression":"compute_stats(default.values__tmp__table__2.tmp_values_col3, 'hll')","edgeType":"PROJECTION"},{"sources":[],"targets":[3],"expression":"compute_stats(UDFToInteger(tmp_values_col4), 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.des t_l3.id"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l3.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l3.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l3.c3"}]} PREHOOK: query: select sum(a.c1) over (partition by a.c1 order by a.id) from dest_l2 a where a.c2 != 10
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/column_access_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/column_access_stats.q.out b/ql/src/test/results/clientpositive/llap/column_access_stats.q.out index 6f02442..7929645 100644 --- a/ql/src/test/results/clientpositive/llap/column_access_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/column_access_stats.q.out @@ -406,19 +406,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -431,10 +431,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 1012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 467 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 1012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 467 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -538,19 +538,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(val) = 3.0) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -564,10 +564,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -639,19 +639,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) = 6.0) and val is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -664,10 +664,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -734,19 +734,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -772,19 +772,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t3 - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -798,16 +798,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 5 Data size: 1012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 467 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 1012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 467 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 1012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 467 Basic stats: COMPLETE Column stats: NONE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -818,10 +818,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1113 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 513 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 1113 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 513 Basic stats: COMPLETE Column stats: NONE 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/3bbc24d2/ql/src/test/results/clientpositive/llap/column_table_stats_orc.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/column_table_stats_orc.q.out b/ql/src/test/results/clientpositive/llap/column_table_stats_orc.q.out index 6e71803..56b376e 100644 --- a/ql/src/test/results/clientpositive/llap/column_table_stats_orc.q.out +++ b/ql/src/test/results/clientpositive/llap/column_table_stats_orc.q.out @@ -35,7 +35,7 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 1 numRows 1 rawDataSize 170 @@ -72,22 +72,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Statistics Aggregation Key Prefix: default.s/ GatherStats: true Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 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>) auto parallelism: false @@ -102,7 +102,7 @@ STAGE PLANS: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value @@ -123,7 +123,7 @@ STAGE PLANS: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value @@ -152,13 +152,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -321,13 +321,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: spart - Statistics: Num rows: 2 Data size: 1812 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 1076 Basic stats: COMPLETE Column stats: PARTIAL Statistics Aggregation Key Prefix: default.spart/ GatherStats: true Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 2 Data size: 1812 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 1076 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) @@ -357,7 +357,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 #### A masked pattern was here #### name default.spart @@ -401,7 +401,7 @@ STAGE PLANS: ds 2008-04-08 hr 12 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 #### A masked pattern was here #### name default.spart @@ -715,13 +715,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: spart - Statistics: Num rows: 1 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: PARTIAL Statistics Aggregation Key Prefix: default.spart/ GatherStats: true Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 1 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), '11' (type: string) @@ -751,7 +751,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 #### A masked pattern was here #### name default.spart @@ -947,7 +947,7 @@ Database: default Table: spart #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 1 numRows 1 rawDataSize 170 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/columnstats_part_coltype.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/columnstats_part_coltype.q.out b/ql/src/test/results/clientpositive/llap/columnstats_part_coltype.q.out index 72f9aa2..fff076e 100644 --- a/ql/src/test/results/clientpositive/llap/columnstats_part_coltype.q.out +++ b/ql/src/test/results/clientpositive/llap/columnstats_part_coltype.q.out @@ -116,16 +116,36 @@ PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') key POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -key int from deserializer +col_name key +data_type int +min 27 +max 484 +num_nulls 0 +distinct_count 20 +avg_col_len +max_col_len +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value PREHOOK: type: DESCTABLE PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -value string from deserializer +col_name value +data_type string +min +max +num_nulls 0 +distinct_count 20 +avg_col_len 6.8 +max_col_len 7 +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr=2, part) compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@partcolstats @@ -186,16 +206,36 @@ PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') key POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -key int from deserializer +col_name key +data_type int +min 27 +max 495 +num_nulls 0 +distinct_count 30 +avg_col_len +max_col_len +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value PREHOOK: type: DESCTABLE PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -value string from deserializer +col_name value +data_type string +min +max +num_nulls 0 +distinct_count 30 +avg_col_len 6.833333333333333 +max_col_len 7 +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr, part) compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@partcolstats @@ -260,32 +300,72 @@ PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') key POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -key int from deserializer +col_name key +data_type int +min 15 +max 495 +num_nulls 0 +distinct_count 40 +avg_col_len +max_col_len +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value PREHOOK: type: DESCTABLE PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -value string from deserializer +col_name value +data_type string +min +max +num_nulls 0 +distinct_count 40 +avg_col_len 6.825 +max_col_len 7 +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key PREHOOK: type: DESCTABLE PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -key int from deserializer +col_name key +data_type int +min 15 +max 495 +num_nulls 0 +distinct_count 58 +avg_col_len +max_col_len +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value PREHOOK: type: DESCTABLE PREHOOK: Input: default@partcolstats POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@partcolstats -# col_name data_type comment -value string from deserializer +col_name value +data_type string +min +max +num_nulls 0 +distinct_count 58 +avg_col_len 6.883333333333334 +max_col_len 7 +num_trues +num_falses +bitVector HL +comment from deserializer PREHOOK: query: analyze table partcolstats partition (ds, hr, part) compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@partcolstats http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out b/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out index 7a48615..3be74ec 100644 --- a/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out +++ b/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out @@ -62,30 +62,30 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Select Operator [SEL_11] (rows=5 width=413) + Select Operator [SEL_11] (rows=1 width=185) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=413) + Merge Join Operator [MERGEJOIN_17] (rows=1 width=94) Conds:RS_8._col3=RS_9._col0(Left Semi),Output:["_col0","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:_col3 - Select Operator [SEL_2] (rows=5 width=376) + Select Operator [SEL_2] (rows=2 width=189) Output:["_col0","_col2","_col3"] - Filter Operator [FIL_15] (rows=5 width=376) + Filter Operator [FIL_15] (rows=2 width=189) predicate:((val = 't1val01') and dimid is not null) - TableScan [TS_0] (rows=10 width=376) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"] + TableScan [TS_0] (rows=10 width=189) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1","dimid"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=2 width=4) Output:["_col0"],keys:_col0 Select Operator [SEL_5] (rows=5 width=4) Output:["_col0"] Filter Operator [FIL_16] (rows=5 width=4) predicate:id is not null TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id where table1.val = 't1val01' PREHOOK: type: QUERY @@ -116,44 +116,44 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=5 width=232) + Select Operator [SEL_17] (rows=1 width=187) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_28] (rows=5 width=232) + Merge Join Operator [MERGEJOIN_28] (rows=1 width=96) Conds:RS_14._col2=RS_15._col0(Left Semi),Output:["_col0","_col4"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_15] PartitionCols:_col0 - Group By Operator [GBY_13] (rows=5 width=4) + Group By Operator [GBY_13] (rows=2 width=4) Output:["_col0"],keys:_col0 Select Operator [SEL_8] (rows=5 width=4) Output:["_col0"] Filter Operator [FIL_26] (rows=5 width=4) predicate:id is not null TableScan [TS_6] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_14] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_27] (rows=5 width=211) + Merge Join Operator [MERGEJOIN_27] (rows=2 width=100) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Select Operator [SEL_2] (rows=5 width=192) + Select Operator [SEL_2] (rows=2 width=99) Output:["_col0","_col2"] - Filter Operator [FIL_24] (rows=5 width=192) + Filter Operator [FIL_24] (rows=2 width=99) predicate:((val = 't1val01') and dimid is not null and id is not null) - TableScan [TS_0] (rows=10 width=192) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","dimid"] + TableScan [TS_0] (rows=10 width=99) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","dimid"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_10] PartitionCols:_col0 - Select Operator [SEL_5] (rows=3 width=188) + Select Operator [SEL_5] (rows=3 width=96) Output:["_col0","_col1"] - Filter Operator [FIL_25] (rows=3 width=188) + Filter Operator [FIL_25] (rows=3 width=96) predicate:id is not null - TableScan [TS_3] (rows=3 width=188) - default@table2,table2,Tbl:COMPLETE,Col:NONE,Output:["id","val2"] + TableScan [TS_3] (rows=3 width=96) + default@table2,table2,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val2"] PREHOOK: query: select table1.id, table1.val, table2.val2 from table1 inner join table2 on table1.val = 't1val01' and table1.id = table2.id left semi join table3 on table1.dimid = table3.id PREHOOK: type: QUERY @@ -186,44 +186,44 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=5 width=232) + Select Operator [SEL_17] (rows=1 width=187) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_28] (rows=5 width=232) + Merge Join Operator [MERGEJOIN_28] (rows=1 width=96) Conds:RS_14._col0=RS_15._col0(Inner),Output:["_col0","_col4"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_15] PartitionCols:_col0 - Select Operator [SEL_8] (rows=3 width=188) + Select Operator [SEL_8] (rows=3 width=96) Output:["_col0","_col1"] - Filter Operator [FIL_26] (rows=3 width=188) + Filter Operator [FIL_26] (rows=3 width=96) predicate:id is not null - TableScan [TS_6] (rows=3 width=188) - default@table2,table2,Tbl:COMPLETE,Col:NONE,Output:["id","val2"] + TableScan [TS_6] (rows=3 width=96) + default@table2,table2,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val2"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_14] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_27] (rows=5 width=211) + Merge Join Operator [MERGEJOIN_27] (rows=1 width=4) Conds:RS_11._col2=RS_12._col0(Left Semi),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_11] PartitionCols:_col2 - Select Operator [SEL_2] (rows=5 width=192) + Select Operator [SEL_2] (rows=2 width=99) Output:["_col0","_col2"] - Filter Operator [FIL_24] (rows=5 width=192) + Filter Operator [FIL_24] (rows=2 width=99) predicate:((val = 't1val01') and dimid is not null and id is not null) - TableScan [TS_0] (rows=10 width=192) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","dimid"] + TableScan [TS_0] (rows=10 width=99) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","dimid"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=5 width=4) + Group By Operator [GBY_10] (rows=2 width=4) Output:["_col0"],keys:_col0 Select Operator [SEL_5] (rows=5 width=4) Output:["_col0"] Filter Operator [FIL_25] (rows=5 width=4) predicate:id is not null TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table2.val2 from table1 left semi join table3 on table1.dimid = table3.id inner join table2 on table1.val = 't1val01' and table1.id = table2.id PREHOOK: type: QUERY @@ -255,28 +255,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=4) + Merge Join Operator [MERGEJOIN_17] (rows=1 width=185) Conds:RS_8.100, true=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:100, true - Select Operator [SEL_2] (rows=1 width=372) + Select Operator [SEL_2] (rows=1 width=193) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_15] (rows=1 width=372) + Filter Operator [FIL_15] (rows=1 width=185) predicate:false - TableScan [TS_0] (rows=10 width=372) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1"] + TableScan [TS_0] (rows=10 width=185) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0, _col1 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=1 width=8) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_5] (rows=5 width=4) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=5 width=4) + Filter Operator [FIL_16] (rows=1 width=4) predicate:(id = 100) TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id and table3.id = 100 where table1.dimid <> 100 PREHOOK: type: QUERY @@ -303,28 +303,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=413) + Merge Join Operator [MERGEJOIN_17] (rows=3 width=185) Conds:RS_8.100, true=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:100, true - Select Operator [SEL_2] (rows=5 width=376) + Select Operator [SEL_2] (rows=3 width=193) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_15] (rows=5 width=376) + Filter Operator [FIL_15] (rows=3 width=189) predicate:(dimid = 100) - TableScan [TS_0] (rows=10 width=376) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"] + TableScan [TS_0] (rows=10 width=189) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1","dimid"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0, _col1 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=1 width=8) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_5] (rows=5 width=4) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=5 width=4) + Filter Operator [FIL_16] (rows=1 width=4) predicate:(id = 100) TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id and table3.id = 100 where table1.dimid IN (100,200) PREHOOK: type: QUERY @@ -353,28 +353,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=4) + Merge Join Operator [MERGEJOIN_17] (rows=1 width=185) Conds:RS_8.100, true=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:100, true - Select Operator [SEL_2] (rows=1 width=372) + Select Operator [SEL_2] (rows=1 width=193) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_15] (rows=1 width=372) + Filter Operator [FIL_15] (rows=1 width=185) predicate:false - TableScan [TS_0] (rows=10 width=372) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1"] + TableScan [TS_0] (rows=10 width=185) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0, _col1 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=1 width=8) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_5] (rows=5 width=4) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=5 width=4) + Filter Operator [FIL_16] (rows=1 width=4) predicate:(id = 100) TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id and table3.id = 100 where table1.dimid = 200 PREHOOK: type: QUERY @@ -401,28 +401,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=413) + Merge Join Operator [MERGEJOIN_17] (rows=3 width=185) Conds:RS_8.100, true=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:100, true - Select Operator [SEL_2] (rows=5 width=376) + Select Operator [SEL_2] (rows=3 width=193) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_15] (rows=5 width=376) + Filter Operator [FIL_15] (rows=3 width=189) predicate:(dimid = 100) - TableScan [TS_0] (rows=10 width=376) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"] + TableScan [TS_0] (rows=10 width=189) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1","dimid"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0, _col1 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=1 width=8) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_5] (rows=5 width=4) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=5 width=4) + Filter Operator [FIL_16] (rows=1 width=4) predicate:(id = 100) TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id and table3.id = 100 where table1.dimid = 100 PREHOOK: type: QUERY @@ -451,28 +451,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=5 width=413) + Merge Join Operator [MERGEJOIN_17] (rows=3 width=185) Conds:RS_8.100, true=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:100, true - Select Operator [SEL_2] (rows=5 width=376) + Select Operator [SEL_2] (rows=3 width=193) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_15] (rows=5 width=376) + Filter Operator [FIL_15] (rows=3 width=189) predicate:(dimid = 100) - TableScan [TS_0] (rows=10 width=376) - default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"] + TableScan [TS_0] (rows=10 width=189) + default@table1,table1,Tbl:COMPLETE,Col:COMPLETE,Output:["id","val","val1","dimid"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0, _col1 - Group By Operator [GBY_7] (rows=5 width=4) + Group By Operator [GBY_7] (rows=1 width=8) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_5] (rows=5 width=4) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=5 width=4) + Filter Operator [FIL_16] (rows=1 width=4) predicate:(id = 100) TableScan [TS_3] (rows=5 width=4) - default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"] + default@table3,table3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: select table1.id, table1.val, table1.val1 from table1 left semi join table3 on table1.dimid = table3.id and table3.id = 100 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out b/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out index 94fe942..76200c6 100644 --- a/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out +++ b/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out @@ -50,14 +50,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -70,14 +70,14 @@ STAGE PLANS: input vertices: 1 Map 2 2 Map 3 - Statistics: Num rows: 22 Data size: 8096 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 8096 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 22 Data size: 8096 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -108,19 +108,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/cte_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/cte_5.q.out b/ql/src/test/results/clientpositive/llap/cte_5.q.out index 5b3c8ca..e7c10aa 100644 --- a/ql/src/test/results/clientpositive/llap/cte_5.q.out +++ b/ql/src/test/results/clientpositive/llap/cte_5.q.out @@ -86,9 +86,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_10] - Select Operator [SEL_9] (rows=2 width=90) + Select Operator [SEL_9] (rows=2 width=4) Output:["_col0"] - Merge Join Operator [MERGEJOIN_13] (rows=2 width=90) + Merge Join Operator [MERGEJOIN_13] (rows=2 width=8) Conds:(Inner) <-Map 1 [XPROD_EDGE] llap XPROD_EDGE [RS_6] @@ -96,7 +96,7 @@ Stage-0 Filter Operator [FIL_11] (rows=1 width=4) predicate:(UDFToDouble(colnum) = 5.0) TableScan [TS_0] (rows=1 width=4) - mydb@q1,a,Tbl:COMPLETE,Col:NONE,Output:["colnum"] + mydb@q1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["colnum"] <-Map 3 [XPROD_EDGE] llap XPROD_EDGE [RS_7] Select Operator [SEL_5] (rows=2 width=85) http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/cte_mat_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/cte_mat_5.q.out b/ql/src/test/results/clientpositive/llap/cte_mat_5.q.out index e75c778..84b5ce3 100644 --- a/ql/src/test/results/clientpositive/llap/cte_mat_5.q.out +++ b/ql/src/test/results/clientpositive/llap/cte_mat_5.q.out @@ -95,7 +95,7 @@ Stage-3 Filter Operator [FIL_18] (rows=1 width=4) predicate:colnum is not null TableScan [TS_5] (rows=1 width=4) - mydb@q1,a,Tbl:COMPLETE,Col:NONE,Output:["colnum"] + mydb@q1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["colnum"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:UDFToDouble(_col0) http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/deleteAnalyze.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/deleteAnalyze.q.out b/ql/src/test/results/clientpositive/llap/deleteAnalyze.q.out index d2552fe..253d5b7 100644 --- a/ql/src/test/results/clientpositive/llap/deleteAnalyze.q.out +++ b/ql/src/test/results/clientpositive/llap/deleteAnalyze.q.out @@ -47,7 +47,7 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"amount\":\"true\",\"id\":\"true\",\"item\":\"true\",\"sales_tax\":\"true\"}} numFiles 1 numRows 2 rawDataSize 634 @@ -73,17 +73,17 @@ POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@testdeci2 col_name amount data_type decimal(10,3) -min -max -num_nulls -distinct_count +min 12.123 +max 123.123 +num_nulls 0 +distinct_count 2 avg_col_len max_col_len num_trues num_falses -bitVector +bitVector HL comment from deserializer -COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} +COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"amount\":\"true\",\"id\":\"true\",\"item\":\"true\",\"sales_tax\":\"true\"}} PREHOOK: query: analyze table testdeci2 compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@testdeci2 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/disable_merge_for_bucketing.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/disable_merge_for_bucketing.q.out b/ql/src/test/results/clientpositive/llap/disable_merge_for_bucketing.q.out index acd6076..e45d49e 100644 --- a/ql/src/test/results/clientpositive/llap/disable_merge_for_bucketing.q.out +++ b/ql/src/test/results/clientpositive/llap/disable_merge_for_bucketing.q.out @@ -140,6 +140,41 @@ STAGE PLANS: TotalFiles: 2 GatherStats: true MultiFileSpray: true + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -177,6 +212,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucket2_1 + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucket2_1 select * from src @@ -212,18 +252,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -233,10 +273,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
