Horton

Re: Partition-wise aggregation/grouping

Jeevan Chalke <jeevan.chalke@enterprisedb.com>

View thread View on postgr.es
From: Jeevan Chalke <jeevan.chalke@enterprisedb.com>
To: Robert Haas <robertmhaas@gmail.com>
Cc: Dilip Kumar <dilipbalaut@gmail.com>, David Rowley <david.rowley@2ndquadrant.com>, Ashutosh Bapat <ashutosh.bapat@enterprisedb.com>, Rajkumar Raghuwanshi <rajkumar.raghuwanshi@enterprisedb.com>, PostgreSQL Hackers <pgsql-hackers@postgresql.org>
Date: 2017-11-01T12:50:11Z
Lists: pgsql-hackers 
On Sat, Oct 28, 2017 at 3:07 PM, Robert Haas <robertmhaas@gmail.com> wrote:

> On Fri, Oct 27, 2017 at 1:01 PM, Jeevan Chalke
> <jeevan.chalke@enterprisedb.com> wrote:
> > 1. Added separate patch for costing Append node as discussed up-front in
> the
> > patch-set.
> > 2. Since we now cost Append node, we don't need
> > partition_wise_agg_cost_factor
> > GUC. So removed that. The remaining patch hence merged into main
> > implementation
> > patch.
> > 3. Updated rows in test-cases so that we will get partition-wise plans.
>
> With 0006 applied, cost_merge_append() is now a little bit confused:
>
>     /*
>      * Also charge a small amount (arbitrarily set equal to operator cost)
> per
>      * extracted tuple.  We don't charge cpu_tuple_cost because a
> MergeAppend
>      * node doesn't do qual-checking or projection, so it has less overhead
>      * than most plan nodes.
>      */
>     run_cost += cpu_operator_cost * tuples;
>
>     /* Add MergeAppend node overhead like we do it for the Append node */
>     run_cost += cpu_tuple_cost * DEFAULT_APPEND_COST_FACTOR * tuples;
>
> The first comment says that we don't add cpu_tuple_cost, and the
> second one then adds half of it anyway.
>

Yep.
But as David reported earlier, if we remove the first part i.e. adding
cpu_operator_cost per tuple, Merge Append will be preferred over an Append
node unlike before. And thus, I thought of better having both, but no so
sure. Should we remove that part altogether, or add both in a single
statement with updated comments?


> I think it's fine to have a #define for DEFAULT_APPEND_COST_FACTOR,
> because as you say it's used twice, but I don't think that should be
> exposed in cost.h; I'd make it private to costsize.c and rename it to
> something like APPEND_CPU_COST_MULTIPLIER.  The word DEFAULT, in
> particular, seems useless to me, since there's no provision for it to
> be overridden by a different value.
>

Agree. Will make that change.


>
> What testing, if any, can we think about doing with this plan to make
> sure it doesn't regress things?  For example, if we do a TPC-H run
> with partitioned tables and partition-wise join enabled, will any
> plans change with this patch?


I have tried doing this on my local developer machine. For 1GB database
size (tpc-h scale factor 1), I see no plan change with and without this
patch.

I have tried with scale factor 10, but query is not executing well due to
space and memory constraints. Can someone try out that?


>   Do they get faster or not?  Anyone have
> other ideas for what to test?
>
> --
> Robert Haas
> EnterpriseDB: http://www.enterprisedb.com
> The Enterprise PostgreSQL Company
>


-- 
Jeevan Chalke
Technical Architect, Product Development
EnterpriseDB Corporation
The Enterprise PostgreSQL Company

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.