| # Sample 10% |
| select * from functional.alltypes tablesample system(10) repeatable(1234) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=32.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=3/24 files=3 size=60.68KB |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=32.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=730 |
| ==== |
| # Sample 50% |
| select * from functional.alltypes tablesample system(50) repeatable(1234) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=80.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=12/24 files=12 size=239.26KB |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=80.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=3650 |
| ==== |
| # Sampling and scan predicates. Scan predicates are evaluated after sampling and |
| # that is reflected in the cardinality. |
| select * from functional.alltypes tablesample system(50) repeatable(1234) |
| where id < 10 |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=80.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=12/24 files=12 size=239.26KB |
| predicates: id < 10 |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| parquet dictionary predicates: id < 10 |
| mem-estimate=80.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=365 |
| ==== |
| # Partition pruning + sampling. Partition pruning happens after sampling. |
| select * from functional.alltypes tablesample system(50) repeatable(1234) |
| where year = 2009 |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=48.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=6/24 files=6 size=119.70KB |
| stats-rows=3650 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=48.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=1825 |
| ==== |
| # Edge case: sample 0%, no files should be selected |
| select * from functional.alltypes tablesample system(0) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=0B mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=0/24 files=0 size=0B |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=0B mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=0 |
| ==== |
| # Edge case: sample 1%, at least one file should be selected |
| select * from functional.alltypes tablesample system(1) repeatable(1234) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=32.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=1/24 files=1 size=19.95KB |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=32.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=73 |
| ==== |
| # Edge case: sample 1% and prune partitions, at least one file should be selected |
| select * from functional.alltypes tablesample system(1) repeatable(1234) |
| where year = 2010 |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=32.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=1/24 files=1 size=20.36KB |
| stats-rows=3650 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=32.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=37 |
| ==== |
| # Edge case: sample 100%, all files should be selected |
| select * from functional.alltypes tablesample system (100) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=128.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=24/24 files=24 size=478.45KB |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=128.00MB mem-reservation=0B |
| tuple-ids=0 row-size=97B cardinality=7300 |
| ==== |
| # Table that has no stats. |
| select id from functional_parquet.alltypes tablesample system(10) repeatable(1234) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=16.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional_parquet.alltypes] |
| partitions=3/24 files=3 size=22.53KB |
| stats-rows=unavailable extrapolated-rows=disabled |
| table stats: rows=unavailable size=unavailable |
| column stats: unavailable |
| mem-estimate=16.00MB mem-reservation=0B |
| tuple-ids=0 row-size=4B cardinality=unavailable |
| ==== |
| # Sampling in a subquery. |
| select id from functional.alltypes t1 where exists ( |
| select id from functional.alltypessmall t2 tablesample system(10) repeatable(1234) |
| where t1.id = t2.id) |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=161.94MB mem-reservation=1.94MB |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 02:HASH JOIN [LEFT SEMI JOIN] |
| | hash predicates: t1.id = t2.id |
| | runtime filters: RF000 <- t2.id |
| | mem-estimate=1.94MB mem-reservation=1.94MB spill-buffer=64.00KB |
| | tuple-ids=0 row-size=4B cardinality=10 |
| | |
| |--01:SCAN HDFS [functional.alltypessmall t2] |
| | partitions=1/4 files=1 size=1.57KB |
| | stats-rows=100 extrapolated-rows=disabled |
| | table stats: rows=100 size=6.32KB |
| | column stats: all |
| | mem-estimate=32.00MB mem-reservation=0B |
| | tuple-ids=1 row-size=4B cardinality=10 |
| | |
| 00:SCAN HDFS [functional.alltypes t1] |
| partitions=24/24 files=24 size=478.45KB |
| runtime filters: RF000 -> t1.id |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=128.00MB mem-reservation=0B |
| tuple-ids=0 row-size=4B cardinality=7300 |
| ==== |
| # Sampling in WITH-clause view. |
| with t as (select * from functional.alltypes tablesample system(10) repeatable(1234)) |
| select id from t |
| ---- PLAN |
| F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1 |
| | Per-Host Resources: mem-estimate=32.00MB mem-reservation=0B |
| PLAN-ROOT SINK |
| | mem-estimate=0B mem-reservation=0B |
| | |
| 00:SCAN HDFS [functional.alltypes] |
| partitions=3/24 files=3 size=60.68KB |
| stats-rows=7300 extrapolated-rows=disabled |
| table stats: rows=7300 size=478.45KB |
| column stats: all |
| mem-estimate=32.00MB mem-reservation=0B |
| tuple-ids=0 row-size=4B cardinality=730 |
| ==== |