database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-21 00:42:43 +03:00
Code Activity

Support parallel aggregation.

Browse Source 
Parallel workers can now partially aggregate the data and pass the
transition values back to the leader, which can combine the partial
results to produce the final answer.

David Rowley, based on earlier work by Haribabu Kommi.  Reviewed by
Álvaro Herrera, Tomas Vondra, Amit Kapila, James Sewell, and me.
This commit is contained in:
Robert Haas
2016-03-21 09:20:53 -04:00
parent 7fa0064092
commit e06a38965b
23 changed files with 910 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/backend/optimizer/path/costsize.c
View File

@@ -350,16 +350,22 @@ cost_samplescan(Path *path, PlannerInfo *root,
*
* 'rel' is the relation to be operated upon
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
* 'rows' may be used to point to a row estimate; if non-NULL, it overrides
* both 'rel' and 'param_info'. This is useful when the path doesn't exactly
* correspond to any particular RelOptInfo.
*/
void
cost_gather(GatherPath *path, PlannerInfo *root,
RelOptInfo *rel, ParamPathInfo *param_info)
RelOptInfo *rel, ParamPathInfo *param_info,
double *rows)
{
Cost startup_cost = 0;
Cost run_cost = 0;
/* Mark the path with the correct row estimate */
if (param_info)
if (rows)
path->path.rows = *rows;
else if (param_info)
path->path.rows = param_info->ppi_rows;
else
path->path.rows = rel->rows;
@@ -1751,6 +1757,8 @@ cost_agg(Path *path, PlannerInfo *root,
{
/* must be AGG_HASHED */
startup_cost = input_total_cost;
if (!enable_hashagg)
startup_cost += disable_cost;
startup_cost += aggcosts->transCost.startup;
startup_cost += aggcosts->transCost.per_tuple * input_tuples;
startup_cost += (cpu_operator_cost * numGroupCols) * input_tuples;