http://git-wip-us.apache.org/repos/asf/impala/blob/2a4835cf/testdata/workloads/functional-planner/queries/PlannerTest/parquet-filtering.test ---------------------------------------------------------------------- diff --git a/testdata/workloads/functional-planner/queries/PlannerTest/parquet-filtering.test b/testdata/workloads/functional-planner/queries/PlannerTest/parquet-filtering.test index a373b96..3ebd0aa 100644 --- a/testdata/workloads/functional-planner/queries/PlannerTest/parquet-filtering.test +++ b/testdata/workloads/functional-planner/queries/PlannerTest/parquet-filtering.test @@ -19,7 +19,7 @@ PLAN-ROOT SINK | in pipelines: 01(GETNEXT), 00(OPEN) | 00:SCAN HDFS [functional_parquet.alltypes] - partitions=24/24 files=24 size=188.92KB + partitions=24/24 files=24 size=189.12KB predicates: int_col IS NULL, int_col > CAST(1 AS INT), int_col > CAST(tinyint_col AS INT), CAST(int_col AS DOUBLE) * rand() > CAST(50 AS DOUBLE) stored statistics: table: rows=unavailable size=unavailable @@ -81,7 +81,7 @@ PLAN-ROOT SINK | in pipelines: 01(GETNEXT), 00(OPEN) | 00:SCAN HDFS [functional_parquet.alltypes] - partitions=22/24 files=22 size=172.93KB + partitions=22/24 files=22 size=173.06KB predicates: bool_col, bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), int_col % CAST(2 AS INT) = CAST(1 AS INT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), timestamp_cmp(timestamp_col, TIMESTAMP '2016-11-20 00:00:00') = CAST(1 AS INT), date_string_col > '1993-10-01' stored statistics: table: rows=unavailable size=unavailable @@ -91,7 +91,7 @@ PLAN-ROOT SINK parquet statistics predicates: bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), date_string_col > '1993-10-01' parquet dictionary predicates: bool_col, bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), int_col % CAST(2 AS INT) = CAST(1 AS INT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), timestamp_cmp(timestamp_col, TIMESTAMP '2016-11-20 00:00:00') = CAST(1 AS INT), date_string_col > '1993-10-01' mem-estimate=128.00MB mem-reservation=88.00KB thread-reservation=1 - tuple-ids=0 row-size=80B cardinality=unavailable + tuple-ids=0 row-size=72B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Test non-parquet files for a variety of predicates @@ -123,7 +123,7 @@ PLAN-ROOT SINK columns: all extrapolated-rows=disabled max-scan-range-rows=339 mem-estimate=128.00MB mem-reservation=32.00KB thread-reservation=1 - tuple-ids=0 row-size=89B cardinality=1 + tuple-ids=0 row-size=81B cardinality=1 in pipelines: 00(GETNEXT) ==== # Test negative cases for IN predicate min/max filtering @@ -148,7 +148,7 @@ PLAN-ROOT SINK | in pipelines: 01(GETNEXT), 00(OPEN) | 00:SCAN HDFS [functional_parquet.alltypes] - partitions=24/24 files=24 size=188.92KB + partitions=24/24 files=24 size=189.12KB predicates: id IN (int_col), id NOT IN (CAST(0 AS INT), CAST(1 AS INT), CAST(2 AS INT)), int_col % CAST(50 AS INT) IN (CAST(0 AS INT), CAST(1 AS INT)), string_col IN ('aaaa', 'bbbb', 'cccc', NULL) stored statistics: table: rows=unavailable size=unavailable @@ -157,7 +157,7 @@ PLAN-ROOT SINK extrapolated-rows=disabled max-scan-range-rows=unavailable parquet dictionary predicates: id NOT IN (CAST(0 AS INT), CAST(1 AS INT), CAST(2 AS INT)), int_col % CAST(50 AS INT) IN (CAST(0 AS INT), CAST(1 AS INT)), string_col IN ('aaaa', 'bbbb', 'cccc', NULL) mem-estimate=48.00MB mem-reservation=24.00KB thread-reservation=1 - tuple-ids=0 row-size=24B cardinality=unavailable + tuple-ids=0 row-size=20B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Test collection types where all collections on the path are required (inner @@ -173,34 +173,34 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=2,1,0 row-size=44B cardinality=unavailable +| tuple-ids=2,1,0 row-size=36B cardinality=unavailable | in pipelines: 00(GETNEXT) | |--08:NESTED LOOP JOIN [CROSS JOIN] -| | mem-estimate=24B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1,0 row-size=44B cardinality=100 +| | mem-estimate=20B mem-reservation=0B thread-reservation=0 +| | tuple-ids=2,1,0 row-size=36B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=24B cardinality=1 +| | tuple-ids=0 row-size=20B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 04:SUBPLAN | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1 row-size=20B cardinality=100 +| | tuple-ids=2,1 row-size=16B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--07:NESTED LOOP JOIN [CROSS JOIN] -| | | mem-estimate=16B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=2,1 row-size=20B cardinality=10 +| | | mem-estimate=12B mem-reservation=0B thread-reservation=0 +| | | tuple-ids=2,1 row-size=16B cardinality=10 | | | in pipelines: 00(GETNEXT) | | | | | |--05:SINGULAR ROW SRC | | | parent-subplan=04 | | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=1 row-size=16B cardinality=1 +| | | tuple-ids=1 row-size=12B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | 06:UNNEST [cn.item a] @@ -227,7 +227,7 @@ PLAN-ROOT SINK parquet statistics predicates on a: a.item.e < CAST(-10 AS INT) parquet dictionary predicates on a: a.item.e < CAST(-10 AS INT) mem-estimate=48.00MB mem-reservation=24.00KB thread-reservation=1 - tuple-ids=0 row-size=24B cardinality=unavailable + tuple-ids=0 row-size=20B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Test collection types where the lower collection in the path is optional @@ -245,24 +245,24 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=2N,1,0 row-size=44B cardinality=unavailable +| tuple-ids=2N,1,0 row-size=36B cardinality=unavailable | in pipelines: 00(GETNEXT) | |--08:SUBPLAN | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2N,1,0 row-size=44B cardinality=10 +| | tuple-ids=2N,1,0 row-size=36B cardinality=10 | | in pipelines: 00(GETNEXT) | | | |--06:NESTED LOOP JOIN [RIGHT OUTER JOIN] | | | predicates: a.item.e < CAST(-10 AS INT) -| | | mem-estimate=40B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=2N,1,0 row-size=44B cardinality=1 +| | | mem-estimate=32B mem-reservation=0B thread-reservation=0 +| | | tuple-ids=2N,1,0 row-size=36B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | |--04:SINGULAR ROW SRC | | | parent-subplan=08 | | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=1,0 row-size=40B cardinality=1 +| | | tuple-ids=1,0 row-size=32B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | 05:UNNEST [cn.item a] @@ -272,14 +272,14 @@ PLAN-ROOT SINK | | in pipelines: 00(GETNEXT) | | | 07:NESTED LOOP JOIN [CROSS JOIN] -| | mem-estimate=24B mem-reservation=0B thread-reservation=0 -| | tuple-ids=1,0 row-size=40B cardinality=10 +| | mem-estimate=20B mem-reservation=0B thread-reservation=0 +| | tuple-ids=1,0 row-size=32B cardinality=10 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=24B cardinality=1 +| | tuple-ids=0 row-size=20B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 03:UNNEST [c.nested_struct.c.d cn] @@ -297,7 +297,7 @@ PLAN-ROOT SINK columns missing stats: id extrapolated-rows=disabled max-scan-range-rows=unavailable mem-estimate=48.00MB mem-reservation=24.00KB thread-reservation=1 - tuple-ids=0 row-size=24B cardinality=unavailable + tuple-ids=0 row-size=20B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Tests collection types where the outer is optional (outer join descent) @@ -313,23 +313,23 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=2,1N,0 row-size=44B cardinality=unavailable +| tuple-ids=2,1N,0 row-size=36B cardinality=unavailable | in pipelines: 00(GETNEXT) | |--08:SUBPLAN | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1N,0 row-size=44B cardinality=10 +| | tuple-ids=2,1N,0 row-size=36B cardinality=10 | | in pipelines: 00(GETNEXT) | | | |--06:NESTED LOOP JOIN [CROSS JOIN] -| | | mem-estimate=40B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=2,1N,0 row-size=44B cardinality=10 +| | | mem-estimate=32B mem-reservation=0B thread-reservation=0 +| | | tuple-ids=2,1N,0 row-size=36B cardinality=10 | | | in pipelines: 00(GETNEXT) | | | | | |--04:SINGULAR ROW SRC | | | parent-subplan=08 | | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=1N,0 row-size=40B cardinality=1 +| | | tuple-ids=1N,0 row-size=32B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | 05:UNNEST [cn.item a] @@ -339,14 +339,14 @@ PLAN-ROOT SINK | | in pipelines: 00(GETNEXT) | | | 07:NESTED LOOP JOIN [RIGHT OUTER JOIN] -| | mem-estimate=24B mem-reservation=0B thread-reservation=0 -| | tuple-ids=1N,0 row-size=40B cardinality=1 +| | mem-estimate=20B mem-reservation=0B thread-reservation=0 +| | tuple-ids=1N,0 row-size=32B cardinality=1 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=24B cardinality=1 +| | tuple-ids=0 row-size=20B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 03:UNNEST [c.nested_struct.c.d cn] @@ -363,7 +363,7 @@ PLAN-ROOT SINK columns missing stats: id extrapolated-rows=disabled max-scan-range-rows=unavailable mem-estimate=48.00MB mem-reservation=24.00KB thread-reservation=1 - tuple-ids=0 row-size=24B cardinality=unavailable + tuple-ids=0 row-size=20B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Test collections so that each level has a filter applied. @@ -377,34 +377,34 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=2,1,0 row-size=56B cardinality=1500000 +| tuple-ids=2,1,0 row-size=48B cardinality=1500000 | in pipelines: 00(GETNEXT) | |--08:NESTED LOOP JOIN [CROSS JOIN] -| | mem-estimate=24B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1,0 row-size=56B cardinality=100 +| | mem-estimate=20B mem-reservation=0B thread-reservation=0 +| | tuple-ids=2,1,0 row-size=48B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=24B cardinality=1 +| | tuple-ids=0 row-size=20B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 04:SUBPLAN | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1 row-size=32B cardinality=100 +| | tuple-ids=2,1 row-size=28B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--07:NESTED LOOP JOIN [CROSS JOIN] -| | | mem-estimate=24B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=2,1 row-size=32B cardinality=10 +| | | mem-estimate=20B mem-reservation=0B thread-reservation=0 +| | | tuple-ids=2,1 row-size=28B cardinality=10 | | | in pipelines: 00(GETNEXT) | | | | | |--05:SINGULAR ROW SRC | | | parent-subplan=04 | | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=1 row-size=24B cardinality=1 +| | | tuple-ids=1 row-size=20B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | 06:UNNEST [o.o_lineitems l] @@ -420,14 +420,14 @@ PLAN-ROOT SINK | in pipelines: 00(GETNEXT) | 00:SCAN HDFS [tpch_nested_parquet.customer c] - partitions=1/1 files=4 size=288.98MB + partitions=1/1 files=4 size=288.99MB predicates: c_custkey > CAST(0 AS BIGINT), !empty(c.c_orders) predicates on o: !empty(o.o_lineitems), o.o_orderkey > CAST(0 AS BIGINT) predicates on l: l.l_partkey > CAST(0 AS BIGINT) stored statistics: - table: rows=150000 size=288.98MB + table: rows=150000 size=288.99MB columns missing stats: c_orders - extrapolated-rows=disabled max-scan-range-rows=44229 + extrapolated-rows=disabled max-scan-range-rows=44225 parquet statistics predicates: c_custkey > CAST(0 AS BIGINT) parquet statistics predicates on o: o.o_orderkey > CAST(0 AS BIGINT) parquet statistics predicates on l: l.l_partkey > CAST(0 AS BIGINT) @@ -435,7 +435,7 @@ PLAN-ROOT SINK parquet dictionary predicates on o: o.o_orderkey > CAST(0 AS BIGINT) parquet dictionary predicates on l: l.l_partkey > CAST(0 AS BIGINT) mem-estimate=264.00MB mem-reservation=16.00MB thread-reservation=1 - tuple-ids=0 row-size=24B cardinality=15000 + tuple-ids=0 row-size=20B cardinality=15000 in pipelines: 00(GETNEXT) ==== # Test collections in a way that would incorrectly apply a min-max @@ -456,18 +456,18 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=1N,0 row-size=20B cardinality=unavailable +| tuple-ids=1N,0 row-size=16B cardinality=unavailable | in pipelines: 00(GETNEXT) | |--04:NESTED LOOP JOIN [RIGHT OUTER JOIN] -| | mem-estimate=16B mem-reservation=0B thread-reservation=0 -| | tuple-ids=1N,0 row-size=20B cardinality=1 +| | mem-estimate=12B mem-reservation=0B thread-reservation=0 +| | tuple-ids=1N,0 row-size=16B cardinality=1 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=16B cardinality=1 +| | tuple-ids=0 row-size=12B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 03:UNNEST [c.int_array] @@ -484,7 +484,7 @@ PLAN-ROOT SINK columns: unavailable extrapolated-rows=disabled max-scan-range-rows=unavailable mem-estimate=16.00MB mem-reservation=8.00KB thread-reservation=1 - tuple-ids=0 row-size=16B cardinality=unavailable + tuple-ids=0 row-size=12B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Multiple nested collection values (at the same nesting level) where dictionary @@ -502,34 +502,34 @@ PLAN-ROOT SINK | 01:SUBPLAN | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| tuple-ids=2,1,0 row-size=162B cardinality=15000000 +| tuple-ids=2,1,0 row-size=126B cardinality=15000000 | in pipelines: 00(GETNEXT) | |--08:NESTED LOOP JOIN [CROSS JOIN] -| | mem-estimate=50B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1,0 row-size=162B cardinality=100 +| | mem-estimate=42B mem-reservation=0B thread-reservation=0 +| | tuple-ids=2,1,0 row-size=126B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--02:SINGULAR ROW SRC | | parent-subplan=01 | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=0 row-size=50B cardinality=1 +| | tuple-ids=0 row-size=42B cardinality=1 | | in pipelines: 00(GETNEXT) | | | 04:SUBPLAN | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | tuple-ids=2,1 row-size=112B cardinality=100 +| | tuple-ids=2,1 row-size=84B cardinality=100 | | in pipelines: 00(GETNEXT) | | | |--07:NESTED LOOP JOIN [CROSS JOIN] -| | | mem-estimate=32B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=2,1 row-size=112B cardinality=10 +| | | mem-estimate=24B mem-reservation=0B thread-reservation=0 +| | | tuple-ids=2,1 row-size=84B cardinality=10 | | | in pipelines: 00(GETNEXT) | | | | | |--05:SINGULAR ROW SRC | | | parent-subplan=04 | | | mem-estimate=0B mem-reservation=0B thread-reservation=0 -| | | tuple-ids=1 row-size=32B cardinality=1 +| | | tuple-ids=1 row-size=24B cardinality=1 | | | in pipelines: 00(GETNEXT) | | | | | 06:UNNEST [o.o_lineitems l] @@ -545,18 +545,18 @@ PLAN-ROOT SINK | in pipelines: 00(GETNEXT) | 00:SCAN HDFS [tpch_nested_parquet.customer c] - partitions=1/1 files=4 size=288.98MB + partitions=1/1 files=4 size=288.99MB predicates: !empty(c.c_orders) predicates on o: !empty(o.o_lineitems) predicates on l: l.l_shipdate = '1994-08-19', l.l_receiptdate = '1994-08-24', l.l_shipmode = 'RAIL', l.l_returnflag = 'R', l.l_comment IS NULL stored statistics: - table: rows=150000 size=288.98MB + table: rows=150000 size=288.99MB columns missing stats: c_orders - extrapolated-rows=disabled max-scan-range-rows=44229 + extrapolated-rows=disabled max-scan-range-rows=44225 parquet statistics predicates on l: l.l_shipdate = '1994-08-19', l.l_receiptdate = '1994-08-24', l.l_shipmode = 'RAIL', l.l_returnflag = 'R' parquet dictionary predicates on l: l.l_shipdate = '1994-08-19', l.l_receiptdate = '1994-08-24', l.l_shipmode = 'RAIL', l.l_returnflag = 'R' mem-estimate=616.00MB mem-reservation=32.00MB thread-reservation=1 - tuple-ids=0 row-size=50B cardinality=150000 + tuple-ids=0 row-size=42B cardinality=150000 in pipelines: 00(GETNEXT) ==== # Test a variety of predicates on a mixed format table. @@ -570,7 +570,7 @@ and timestamp_cmp(timestamp_col, '2016-11-20 00:00:00') = 1 and year > 2000 and month < 12; ---- PLAN F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 -| Per-Host Resources: mem-estimate=42.00MB mem-reservation=88.00KB thread-reservation=2 +| Per-Host Resources: mem-estimate=138.00MB mem-reservation=88.00KB thread-reservation=2 PLAN-ROOT SINK | mem-estimate=0B mem-reservation=0B thread-reservation=0 | @@ -581,7 +581,7 @@ PLAN-ROOT SINK | in pipelines: 01(GETNEXT), 00(OPEN) | 00:SCAN HDFS [functional.alltypesmixedformat] - partitions=4/4 files=4 size=66.61KB + partitions=4/4 files=4 size=66.09KB predicates: bool_col, bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), int_col % CAST(2 AS INT) = CAST(1 AS INT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), timestamp_cmp(timestamp_col, TIMESTAMP '2016-11-20 00:00:00') = CAST(1 AS INT), date_string_col > '1993-10-01' stored statistics: table: rows=unavailable size=unavailable @@ -591,7 +591,7 @@ PLAN-ROOT SINK parquet statistics predicates: bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), date_string_col > '1993-10-01' parquet dictionary predicates: bool_col, bigint_col < CAST(5000 AS BIGINT), double_col > CAST(100.00 AS DOUBLE), float_col > CAST(50.00 AS FLOAT), id = CAST(1 AS INT), tinyint_col < CAST(50 AS TINYINT), int_col % CAST(2 AS INT) = CAST(1 AS INT), string_col IN ('aaaa', 'bbbb', 'cccc'), smallint_col IN (CAST(1 AS SMALLINT), CAST(2 AS SMALLINT), CAST(3 AS SMALLINT), CAST(4 AS SMALLINT), CAST(5 AS SMALLINT)), timestamp_cmp(timestamp_col, TIMESTAMP '2016-11-20 00:00:00') = CAST(1 AS INT), date_string_col > '1993-10-01' mem-estimate=128.00MB mem-reservation=88.00KB thread-reservation=1 - tuple-ids=0 row-size=80B cardinality=unavailable + tuple-ids=0 row-size=72B cardinality=unavailable in pipelines: 00(GETNEXT) ==== # Test a variety of predicates on a mixed format table. @@ -624,6 +624,6 @@ PLAN-ROOT SINK columns missing stats: id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col, double_col, date_string_col, string_col, timestamp_col extrapolated-rows=disabled max-scan-range-rows=0 mem-estimate=0B mem-reservation=0B thread-reservation=0 - tuple-ids=0 row-size=80B cardinality=0 + tuple-ids=0 row-size=72B cardinality=0 in pipelines: 00(GETNEXT) ====
http://git-wip-us.apache.org/repos/asf/impala/blob/2a4835cf/testdata/workloads/functional-planner/queries/PlannerTest/partition-pruning.test ---------------------------------------------------------------------- diff --git a/testdata/workloads/functional-planner/queries/PlannerTest/partition-pruning.test b/testdata/workloads/functional-planner/queries/PlannerTest/partition-pruning.test index fa16718..768106c 100644 --- a/testdata/workloads/functional-planner/queries/PlannerTest/partition-pruning.test +++ b/testdata/workloads/functional-planner/queries/PlannerTest/partition-pruning.test @@ -16,6 +16,6 @@ PLAN-ROOT SINK columns: all extrapolated-rows=disabled max-scan-range-rows=1 mem-estimate=32.00MB mem-reservation=8.00KB thread-reservation=1 - tuple-ids=0 row-size=20B cardinality=1 + tuple-ids=0 row-size=16B cardinality=1 in pipelines: 00(GETNEXT) ====
