diff options
Diffstat (limited to 'src/backend/optimizer/path/costsize.c')
| -rw-r--r-- | src/backend/optimizer/path/costsize.c | 25 |
1 files changed, 23 insertions, 2 deletions
diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c index 877827dcb52..c3daacd3ea6 100644 --- a/src/backend/optimizer/path/costsize.c +++ b/src/backend/optimizer/path/costsize.c @@ -129,6 +129,7 @@ bool enable_hashjoin = true; bool enable_gathermerge = true; bool enable_partition_wise_join = false; bool enable_parallel_append = true; +bool enable_parallel_hash = true; typedef struct { @@ -3130,16 +3131,19 @@ initial_cost_hashjoin(PlannerInfo *root, JoinCostWorkspace *workspace, JoinType jointype, List *hashclauses, Path *outer_path, Path *inner_path, - JoinPathExtraData *extra) + JoinPathExtraData *extra, + bool parallel_hash) { Cost startup_cost = 0; Cost run_cost = 0; double outer_path_rows = outer_path->rows; double inner_path_rows = inner_path->rows; + double inner_path_rows_total = inner_path_rows; int num_hashclauses = list_length(hashclauses); int numbuckets; int numbatches; int num_skew_mcvs; + size_t space_allowed; /* unused */ /* cost of source data */ startup_cost += outer_path->startup_cost; @@ -3161,6 +3165,15 @@ initial_cost_hashjoin(PlannerInfo *root, JoinCostWorkspace *workspace, run_cost += cpu_operator_cost * num_hashclauses * outer_path_rows; /* + * If this is a parallel hash build, then the value we have for + * inner_rows_total currently refers only to the rows returned by each + * participant. For shared hash table size estimation, we need the total + * number, so we need to undo the division. + */ + if (parallel_hash) + inner_path_rows_total *= get_parallel_divisor(inner_path); + + /* * Get hash table size that executor would use for inner relation. * * XXX for the moment, always assume that skew optimization will be @@ -3170,9 +3183,12 @@ initial_cost_hashjoin(PlannerInfo *root, JoinCostWorkspace *workspace, * XXX at some point it might be interesting to try to account for skew * optimization in the cost estimate, but for now, we don't. */ - ExecChooseHashTableSize(inner_path_rows, + ExecChooseHashTableSize(inner_path_rows_total, inner_path->pathtarget->width, true, /* useskew */ + parallel_hash, /* try_combined_work_mem */ + outer_path->parallel_workers, + &space_allowed, &numbuckets, &numbatches, &num_skew_mcvs); @@ -3204,6 +3220,7 @@ initial_cost_hashjoin(PlannerInfo *root, JoinCostWorkspace *workspace, workspace->run_cost = run_cost; workspace->numbuckets = numbuckets; workspace->numbatches = numbatches; + workspace->inner_rows_total = inner_path_rows_total; } /* @@ -3226,6 +3243,7 @@ final_cost_hashjoin(PlannerInfo *root, HashPath *path, Path *inner_path = path->jpath.innerjoinpath; double outer_path_rows = outer_path->rows; double inner_path_rows = inner_path->rows; + double inner_path_rows_total = workspace->inner_rows_total; List *hashclauses = path->path_hashclauses; Cost startup_cost = workspace->startup_cost; Cost run_cost = workspace->run_cost; @@ -3266,6 +3284,9 @@ final_cost_hashjoin(PlannerInfo *root, HashPath *path, /* mark the path with estimated # of batches */ path->num_batches = numbatches; + /* store the total number of tuples (sum of partial row estimates) */ + path->inner_rows_total = inner_path_rows_total; + /* and compute the number of "virtual" buckets in the whole join */ virtualbuckets = (double) numbuckets * (double) numbatches; |