Files
impala/testdata/workloads/functional-planner/queries/PlannerTest/disable-codegen.test
Tim Armstrong b2ebf3de36 IMPALA-5648: fix count(*) mem estimate regression
The metadata-only scan doesn't allocate I/O buffers, contrary to
an assumption of the memory estimation code in the planner.

This fix also sets a floor on the memory estimate, to avoid
estimating 0 bytes. 1MB seems like a reasonable approximation:
I ran metadata-only scans on a few different data sizes and
saw numbers from 128kb to 1mb.

The estimate is now much closer to actual consumption
(it was 80MB before):

  [localhost:21000] > select count(*) from tpch_parquet.lineitem; summary;
  Query: select count(*) from tpch_parquet.lineitem
  Query submitted at: 2017-08-23 11:58:29 (Coordinator: http://tarmstrong-box:25000)
  Query progress can be monitored at: http://tarmstrong-box:25000/query_plan?query_id=cb4b8d41fc838c9a:c5496ff300000000
  +----------+
  | count(*) |
  +----------+
  | 6001215  |
  +----------+
  Fetched 1 row(s) in 0.13s
  +--------------+--------+----------+----------+-------+------------+-----------+---------------+-----------------------+
  | Operator     | #Hosts | Avg Time | Max Time | #Rows | Est. #Rows | Peak Mem  | Est. Peak Mem | Detail                |
  +--------------+--------+----------+----------+-------+------------+-----------+---------------+-----------------------+
  | 03:AGGREGATE | 1      | 168.49us | 168.49us | 1     | 1          | 28.00 KB  | 10.00 MB      | FINALIZE              |
  | 02:EXCHANGE  | 1      | 30.11ms  | 30.11ms  | 3     | 1          | 0 B       | 0 B           | UNPARTITIONED         |
  | 01:AGGREGATE | 3      | 2.05us   | 6.14us   | 3     | 1          | 20.00 KB  | 10.00 MB      |                       |
  | 00:SCAN HDFS | 3      | 4.58ms   | 4.72ms   | 3     | 6.00M      | 128.00 KB | 1.00 MB       | tpch_parquet.lineitem |
  +--------------+--------+----------+----------+-------+------------+-----------+---------------+-----------------------+

Testing:
Updated affected planner tests.

Change-Id: Iaf5c2316bef2afae54a94245c715534ed294f286
Reviewed-on: http://gerrit.cloudera.org:8080/7783
Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com>
Tested-by: Impala Public Jenkins
2017-08-24 06:55:08 +00:00

233 lines
5.6 KiB
Plaintext

# Rows per node is < 3000: codegen should be disabled.
select count(*) from functional.alltypes
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=148.00MB
Codegen disabled by planner
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
02:EXCHANGE [UNPARTITIONED]
|
01:AGGREGATE
| output: count(*)
|
00:SCAN HDFS [functional.alltypes]
partitions=24/24 files=24 size=478.45KB
====
# Rows per node is > 3000: codegen should be enabled.
select count(*) from functional.alltypesagg
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=100.00MB
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
02:EXCHANGE [UNPARTITIONED]
|
01:AGGREGATE
| output: count(*)
|
00:SCAN HDFS [functional.alltypesagg]
partitions=11/11 files=11 size=814.73KB
====
# No stats on functional_parquet: codegen should be disabled.
select count(*) from functional_parquet.alltypes
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=21.00MB
WARNING: The following tables are missing relevant table and/or column statistics.
functional_parquet.alltypes
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
02:EXCHANGE [UNPARTITIONED]
|
01:AGGREGATE
| output: sum_init_zero(functional_parquet.alltypes.parquet-stats: num_rows)
|
00:SCAN HDFS [functional_parquet.alltypes]
partitions=24/24 files=24 size=178.13KB
====
# > 3000 rows returned to coordinator: codegen should be enabled
select * from functional_parquet.alltypes
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=128.00MB
WARNING: The following tables are missing relevant table and/or column statistics.
functional_parquet.alltypes
PLAN-ROOT SINK
|
01:EXCHANGE [UNPARTITIONED]
|
00:SCAN HDFS [functional_parquet.alltypes]
partitions=24/24 files=24 size=178.13KB
====
# Optimisation is enabled for join producing < 3000 rows
select count(*)
from functional.alltypes t1
join functional.alltypestiny t2 on t1.id = t2.id
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=1.94MB
Per-Host Resource Estimates: Memory=181.94MB
Codegen disabled by planner
PLAN-ROOT SINK
|
06:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
05:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: count(*)
|
02:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: t1.id = t2.id
| runtime filters: RF000 <- t2.id
|
|--04:EXCHANGE [BROADCAST]
| |
| 01:SCAN HDFS [functional.alltypestiny t2]
| partitions=4/4 files=4 size=460B
|
00:SCAN HDFS [functional.alltypes t1]
partitions=24/24 files=24 size=478.45KB
runtime filters: RF000 -> t1.id
====
# Optimisation is disabled by cross join producing > 3000 rows
select count(*) from functional.alltypes t1, functional.alltypes t2
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=276.00MB
PLAN-ROOT SINK
|
06:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
05:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: count(*)
|
02:NESTED LOOP JOIN [CROSS JOIN, BROADCAST]
|
|--04:EXCHANGE [BROADCAST]
| |
| 01:SCAN HDFS [functional.alltypes t2]
| partitions=24/24 files=24 size=478.45KB
|
00:SCAN HDFS [functional.alltypes t1]
partitions=24/24 files=24 size=478.45KB
====
# Optimisation is enabled for union producing < 3000 rows
select count(*) from (
select * from functional.alltypes
union all
select * from functional.alltypestiny) v
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=148.00MB
Codegen disabled by planner
PLAN-ROOT SINK
|
05:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
04:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: count(*)
|
00:UNION
| pass-through-operands: all
|
|--02:SCAN HDFS [functional.alltypestiny]
| partitions=4/4 files=4 size=460B
|
01:SCAN HDFS [functional.alltypes]
partitions=24/24 files=24 size=478.45KB
====
# Optimisation is disabled by union producing > 3000 rows
select count(*) from (
select * from functional.alltypes
union all
select * from functional.alltypes) v
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=148.00MB
PLAN-ROOT SINK
|
05:AGGREGATE [FINALIZE]
| output: count:merge(*)
|
04:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: count(*)
|
00:UNION
| pass-through-operands: all
|
|--02:SCAN HDFS [functional.alltypes]
| partitions=24/24 files=24 size=478.45KB
|
01:SCAN HDFS [functional.alltypes]
partitions=24/24 files=24 size=478.45KB
====
# Scan with limit on large table: the number of rows scanned is bounded,
# codegen should be disabled
select sum(l_discount)
from (select * from tpch.lineitem limit 1000) v
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=274.00MB
Codegen disabled by planner
PLAN-ROOT SINK
|
01:AGGREGATE [FINALIZE]
| output: sum(tpch.lineitem.l_discount)
|
02:EXCHANGE [UNPARTITIONED]
| limit: 1000
|
00:SCAN HDFS [tpch.lineitem]
partitions=1/1 files=1 size=718.94MB
limit: 1000
====
# Scan with limit and predicates on large table: any number of rows could be scanned:
# codegen should be enabled
select sum(l_discount)
from (select * from tpch.lineitem where l_orderkey > 100 limit 1000) v
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=0B
Per-Host Resource Estimates: Memory=274.00MB
PLAN-ROOT SINK
|
01:AGGREGATE [FINALIZE]
| output: sum(tpch.lineitem.l_discount)
|
02:EXCHANGE [UNPARTITIONED]
| limit: 1000
|
00:SCAN HDFS [tpch.lineitem]
partitions=1/1 files=1 size=718.94MB
predicates: l_orderkey > 100
limit: 1000
====