Horton

Re: Partition-wise aggregation/grouping

David Rowley <david.rowley@2ndquadrant.com>

View thread View on postgr.es
From: David Rowley <david.rowley@2ndquadrant.com>
To: Ashutosh Bapat <ashutosh.bapat@enterprisedb.com>
Cc: Jeevan Chalke <jeevan.chalke@enterprisedb.com>, Rajkumar Raghuwanshi <rajkumar.raghuwanshi@enterprisedb.com>, PostgreSQL Hackers <pgsql-hackers@postgresql.org>
Date: 2017-10-10T08:01:44Z
Lists: pgsql-hackers 
On 10 October 2017 at 17:57, Ashutosh Bapat
<ashutosh.bapat@enterprisedb.com> wrote:
> Append node just returns the result of ExecProcNode(). Charging
> cpu_tuple_cost may make it too expensive. In other places where we
> charge cpu_tuple_cost there's some processing done to the tuple like
> ExecStoreTuple() in SeqNext(). May be we need some other measure for
> Append's processing of the tuple.

I don't think there's any need to invent any new GUC. You could just
divide cpu_tuple_cost by something.

I did a quick benchmark on my laptop to see how much Append really
costs, and with the standard costs the actual cost seems to be about
cpu_tuple_cost / 2.4. So probably cpu_tuple_cost / 2 might be
realistic. create_set_projection_path() does something similar and
brincostestimate() does some similar magic and applies 0.1 *
cpu_operator_cost to the total cost.

# create table p (a int, b int);
# create table p1 () inherits (p);
# insert into p1 select generate_series(1,1000000);
# vacuum analyze p1;
# \q
$ echo "select count(*) from p1;" > p1.sql
$ echo "select count(*) from p;" > p.sql
$ pgbench -T 60 -f p1.sql -n

latency average = 58.567 ms

$ pgbench -T 60 -f p.sql -n
latency average = 72.984 ms

$ psql
psql (11devel)
Type "help" for help.

# -- check the cost of the plan.
# explain select count(*) from p1;
                            QUERY PLAN
------------------------------------------------------------------
 Aggregate  (cost=16925.00..16925.01 rows=1 width=8)
   ->  Seq Scan on p1  (cost=0.00..14425.00 rows=1000000 width=0)
(2 rows)

# -- selecting from the parent is the same due to zero Append cost.
# explain select count(*) from p;
                               QUERY PLAN
------------------------------------------------------------------------
 Aggregate  (cost=16925.00..16925.01 rows=1 width=8)
   ->  Append  (cost=0.00..14425.00 rows=1000001 width=0)
         ->  Seq Scan on p  (cost=0.00..0.00 rows=1 width=0)
         ->  Seq Scan on p1  (cost=0.00..14425.00 rows=1000000 width=0)
(4 rows)

# -- extrapolate the additional time taken for the Append scan and
work out what the planner
# -- should add to the plan's cost, then divide by the number of rows
in p1 to work out the
# -- tuple cost of pulling a row through the append.
# select (16925.01 * (72.984 / 58.567) - 16925.01)  / 1000000;
        ?column?
------------------------
 0.00416630302337493743
(1 row)

# show cpu_tuple_cost;
 cpu_tuple_cost
----------------
 0.01
(1 row)

# -- How does that compare to the cpu_tuple_cost?
# select current_Setting('cpu_tuple_cost')::float8 / 0.00416630302337493743;
    ?column?
----------------
 2.400209476818
(1 row)

Maybe it's worth trying with different row counts to see if the
additional cost is consistent, but it's probably not worth being too
critical here.

-- 
 David Rowley                   http://www.2ndQuadrant.com/
 PostgreSQL Development, 24x7 Support, Training & Services

Commits

  1. postgres_fdw: Push down partition-wise aggregation.

  2. Remove 'target' from GroupPathExtraData.

  3. Implement partition-wise grouping/aggregation.

  4. Don't pass the grouping target around unnecessarily.

  5. Determine grouping strategies in create_grouping_paths.

  6. Defer creation of partially-grouped relation until it's needed.

  7. Split create_grouping_paths into degenerate and non-degenerate cases.

  8. Pass additional arguments to a couple of grouping-related functions.

  9. Fix logic error in add_paths_to_partial_grouping_rel.

  10. Minor cleanup of code related to partially_grouped_rel.

  11. Add a new upper planner relation for partially-aggregated results.

  12. Charge cpu_tuple_cost * 0.5 for Append and MergeAppend nodes.

  13. Rename enable_partition_wise_join to enable_partitionwise_join

  14. Factor some code out of create_grouping_paths.

  15. Pad XLogReaderState's main_data buffer more aggressively.

  16. Prevent int128 from requiring more than MAXALIGN alignment.

  17. Fix DROP SUBSCRIPTION hang

  18. Inject $(ICU_LIBS) regardless of platform.

  19. Some preliminary refactoring towards partitionwise join.