database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Support parallel btree index builds.

Browse Source 
To make this work, tuplesort.c and logtape.c must also support
parallelism, so this patch adds that infrastructure and then applies
it to the particular case of parallel btree index builds.  Testing
to date shows that this can often be 2-3x faster than a serial
index build.

The model for deciding how many workers to use is fairly primitive
at present, but it's better than not having the feature.  We can
refine it as we get more experience.

Peter Geoghegan with some help from Rushabh Lathia.  While Heikki
Linnakangas is not an author of this patch, he wrote other patches
without which this feature would not have been possible, and
therefore the release notes should possibly credit him as an author
of this feature.  Reviewed by Claudio Freire, Heikki Linnakangas,
Thomas Munro, Tels, Amit Kapila, me.

Discussion: http://postgr.es/m/CAM3SWZQKM=Pzc=CAHzRixKjp2eO5Q0Jg1SoFQqeXFQ647JiwqQ@mail.gmail.com
Discussion: http://postgr.es/m/CAH2-Wz=AxWqDoVvGU7dq856S4r6sJAj6DBn7VMtigkB33N5eyg@mail.gmail.com
This commit is contained in:
Robert Haas
2018-02-02 13:25:55 -05:00
parent 9aef173163
commit 9da0cc3528
51 changed files with 2238 additions and 362 deletions
Download Patch File Download Diff File Expand all files Collapse all files

136
src/backend/optimizer/plan/planner.c
View File

@ -5793,6 +5793,142 @@ plan_cluster_use_sort(Oid tableOid, Oid indexOid)
return (seqScanAndSortPath.total_cost < indexScanPath->path.total_cost);
}
/*
* plan_create_index_workers
* Use the planner to decide how many parallel worker processes
* CREATE INDEX should request for use
*
* tableOid is the table on which the index is to be built. indexOid is the
* OID of an index to be created or reindexed (which must be a btree index).
*
* Return value is the number of parallel worker processes to request. It
* may be unsafe to proceed if this is 0. Note that this does not include the
* leader participating as a worker (value is always a number of parallel
* worker processes).
*
* Note: caller had better already hold some type of lock on the table and
* index.
*/
int
plan_create_index_workers(Oid tableOid, Oid indexOid)
{
PlannerInfo *root;
Query *query;
PlannerGlobal *glob;
RangeTblEntry *rte;
Relation heap;
Relation index;
RelOptInfo *rel;
int parallel_workers;
BlockNumber heap_blocks;
double reltuples;
double allvisfrac;
/* Return immediately when parallelism disabled */
if (max_parallel_maintenance_workers == 0)
return 0;
/* Set up largely-dummy planner state */
query = makeNode(Query);
query->commandType = CMD_SELECT;
glob = makeNode(PlannerGlobal);
root = makeNode(PlannerInfo);
root->parse = query;
root->glob = glob;
root->query_level = 1;
root->planner_cxt = CurrentMemoryContext;
root->wt_param_id = -1;
/*
* Build a minimal RTE.
*
* Set the target's table to be an inheritance parent. This is a kludge
* that prevents problems within get_relation_info(), which does not
* expect that any IndexOptInfo is currently undergoing REINDEX.
*/
rte = makeNode(RangeTblEntry);
rte->rtekind = RTE_RELATION;
rte->relid = tableOid;
rte->relkind = RELKIND_RELATION; /* Don't be too picky. */
rte->lateral = false;
rte->inh = true;
rte->inFromCl = true;
query->rtable = list_make1(rte);
/* Set up RTE/RelOptInfo arrays */
setup_simple_rel_arrays(root);
/* Build RelOptInfo */
rel = build_simple_rel(root, 1, NULL);
heap = heap_open(tableOid, NoLock);
index = index_open(indexOid, NoLock);
/*
* Determine if it's safe to proceed.
*
* Currently, parallel workers can't access the leader's temporary tables.
* Furthermore, any index predicate or index expressions must be parallel
* safe.
*/
if (heap->rd_rel->relpersistence == RELPERSISTENCE_TEMP ||
!is_parallel_safe(root, (Node *) RelationGetIndexExpressions(index)) ||
!is_parallel_safe(root, (Node *) RelationGetIndexPredicate(index)))
{
parallel_workers = 0;
goto done;
}
/*
* If parallel_workers storage parameter is set for the table, accept that
* as the number of parallel worker processes to launch (though still cap
* at max_parallel_maintenance_workers). Note that we deliberately do not
* consider any other factor when parallel_workers is set. (e.g., memory
* use by workers.)
*/
if (rel->rel_parallel_workers != -1)
{
parallel_workers = Min(rel->rel_parallel_workers,
max_parallel_maintenance_workers);
goto done;
}
/*
* Estimate heap relation size ourselves, since rel->pages cannot be
* trusted (heap RTE was marked as inheritance parent)
*/
estimate_rel_size(heap, NULL, &heap_blocks, &reltuples, &allvisfrac);
/*
* Determine number of workers to scan the heap relation using generic
* model
*/
parallel_workers = compute_parallel_worker(rel, heap_blocks, -1,
max_parallel_maintenance_workers);
/*
* Cap workers based on available maintenance_work_mem as needed.
*
* Note that each tuplesort participant receives an even share of the
* total maintenance_work_mem budget. Aim to leave participants
* (including the leader as a participant) with no less than 32MB of
* memory. This leaves cases where maintenance_work_mem is set to 64MB
* immediately past the threshold of being capable of launching a single
* parallel worker to sort.
*/
while (parallel_workers > 0 &&
maintenance_work_mem / (parallel_workers + 1) < 32768L)
parallel_workers--;
done:
index_close(index, NoLock);
heap_close(heap, NoLock);
return parallel_workers;
}
/*
* get_partitioned_child_rels
* Returns a list of the RT indexes of the partitioned child relations