database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-07 00:36:50 +03:00
Code Activity

Redesign tablesample method API, and do extensive code review.

Browse Source 
The original implementation of TABLESAMPLE modeled the tablesample method
API on index access methods, which wasn't a good choice because, without
specialized DDL commands, there's no way to build an extension that can
implement a TSM.  (Raw inserts into system catalogs are not an acceptable
thing to do, because we can't undo them during DROP EXTENSION, nor will
pg_upgrade behave sanely.)  Instead adopt an API more like procedural
language handlers or foreign data wrappers, wherein the only SQL-level
support object needed is a single handler function identified by having
a special return type.  This lets us get rid of the supporting catalog
altogether, so that no custom DDL support is needed for the feature.

Adjust the API so that it can support non-constant tablesample arguments
(the original coding assumed we could evaluate the argument expressions at
ExecInitSampleScan time, which is undesirable even if it weren't outright
unsafe), and discourage sampling methods from looking at invisible tuples.
Make sure that the BERNOULLI and SYSTEM methods are genuinely repeatable
within and across queries, as required by the SQL standard, and deal more
honestly with methods that can't support that requirement.

Make a full code-review pass over the tablesample additions, and fix
assorted bugs, omissions, infelicities, and cosmetic issues (such as
failure to put the added code stanzas in a consistent ordering).
Improve EXPLAIN's output of tablesample plans, too.

Back-patch to 9.5 so that we don't have to support the original API
in production.
This commit is contained in:
Tom Lane
2015-07-25 14:39:00 -04:00
parent b26e3d660d
commit dd7a8f66ed
83 changed files with 3184 additions and 2589 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
src/backend/optimizer/path/allpaths.c
View File

@ -18,6 +18,7 @@
#include <math.h>
#include "access/sysattr.h"
#include "access/tsmapi.h"
#include "catalog/pg_class.h"
#include "catalog/pg_operator.h"
#include "foreign/fdwapi.h"
@ -390,7 +391,7 @@ set_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
}
else if (rte->tablesample != NULL)
{
/* Build sample scan on relation */
/* Sampled relation */
set_tablesample_rel_pathlist(root, rel, rte);
}
else
@ -480,11 +481,40 @@ set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
/*
* set_tablesample_rel_size
* Set size estimates for a sampled relation.
* Set size estimates for a sampled relation
*/
static void
set_tablesample_rel_size(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
TableSampleClause *tsc = rte->tablesample;
TsmRoutine *tsm;
BlockNumber pages;
double tuples;
/*
* Test any partial indexes of rel for applicability. We must do this
* first since partial unique indexes can affect size estimates.
*/
check_partial_indexes(root, rel);
/*
* Call the sampling method's estimation function to estimate the number
* of pages it will read and the number of tuples it will return. (Note:
* we assume the function returns sane values.)
*/
tsm = GetTsmRoutine(tsc->tsmhandler);
tsm->SampleScanGetSampleSize(root, rel, tsc->args,
&pages, &tuples);
/*
* For the moment, because we will only consider a SampleScan path for the
* rel, it's okay to just overwrite the pages and tuples estimates for the
* whole relation. If we ever consider multiple path types for sampled
* rels, we'll need more complication.
*/
rel->pages = pages;
rel->tuples = tuples;
/* Mark rel with estimated output rows, width, etc */
set_baserel_size_estimates(root, rel);
}
@ -492,8 +522,6 @@ set_tablesample_rel_size(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
/*
* set_tablesample_rel_pathlist
* Build access paths for a sampled relation
*
* There is only one possible path - sampling scan
*/
static void
set_tablesample_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
@ -502,15 +530,41 @@ set_tablesample_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *
Path *path;
/*
* We don't support pushing join clauses into the quals of a seqscan, but
* it could still have required parameterization due to LATERAL refs in
* its tlist.
* We don't support pushing join clauses into the quals of a samplescan,
* but it could still have required parameterization due to LATERAL refs
* in its tlist or TABLESAMPLE arguments.
*/
required_outer = rel->lateral_relids;
/* We only do sample scan if it was requested */
/* Consider sampled scan */
path = create_samplescan_path(root, rel, required_outer);
rel->pathlist = list_make1(path);
/*
* If the sampling method does not support repeatable scans, we must avoid
* plans that would scan the rel multiple times. Ideally, we'd simply
* avoid putting the rel on the inside of a nestloop join; but adding such
* a consideration to the planner seems like a great deal of complication
* to support an uncommon usage of second-rate sampling methods. Instead,
* if there is a risk that the query might perform an unsafe join, just
* wrap the SampleScan in a Materialize node. We can check for joins by
* counting the membership of all_baserels (note that this correctly
* counts inheritance trees as single rels). If we're inside a subquery,
* we can't easily check whether a join might occur in the outer query, so
* just assume one is possible.
*
* GetTsmRoutine is relatively expensive compared to the other tests here,
* so check repeatable_across_scans last, even though that's a bit odd.
*/
if ((root->query_level > 1 ||
bms_membership(root->all_baserels) != BMS_SINGLETON) &&
!(GetTsmRoutine(rte->tablesample->tsmhandler)->repeatable_across_scans))
{
path = (Path *) create_material_path(rel, path);
}
add_path(rel, path);
/* For the moment, at least, there are no other paths to consider */
}
/*
@ -2450,7 +2504,33 @@ print_path(PlannerInfo *root, Path *path, int indent)
switch (nodeTag(path))
{
case T_Path:
ptype = "SeqScan";
switch (path->pathtype)
{
case T_SeqScan:
ptype = "SeqScan";
break;
case T_SampleScan:
ptype = "SampleScan";
break;
case T_SubqueryScan:
ptype = "SubqueryScan";
break;
case T_FunctionScan:
ptype = "FunctionScan";
break;
case T_ValuesScan:
ptype = "ValuesScan";
break;
case T_CteScan:
ptype = "CteScan";
break;
case T_WorkTableScan:
ptype = "WorkTableScan";
break;
default:
ptype = "???Path";
break;
}
break;
case T_IndexPath:
ptype = "IdxScan";

57
src/backend/optimizer/path/costsize.c
View File

@ -74,6 +74,7 @@
#include <math.h>
#include "access/htup_details.h"
#include "access/tsmapi.h"
#include "executor/executor.h"
#include "executor/nodeHash.h"
#include "miscadmin.h"
@ -223,64 +224,66 @@ cost_seqscan(Path *path, PlannerInfo *root,
* cost_samplescan
* Determines and returns the cost of scanning a relation using sampling.
*
* From planner/optimizer perspective, we don't care all that much about cost
* itself since there is always only one scan path to consider when sampling
* scan is present, but number of rows estimation is still important.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_samplescan(Path *path, PlannerInfo *root, RelOptInfo *baserel)
cost_samplescan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
RangeTblEntry *rte;
TableSampleClause *tsc;
TsmRoutine *tsm;
double spc_seq_page_cost,
spc_random_page_cost,
spc_page_cost;
QualCost qpqual_cost;
Cost cpu_per_tuple;
BlockNumber pages;
double tuples;
RangeTblEntry *rte = planner_rt_fetch(baserel->relid, root);
TableSampleClause *tablesample = rte->tablesample;
/* Should only be applied to base relations */
/* Should only be applied to base relations with tablesample clauses */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
rte = planner_rt_fetch(baserel->relid, root);
Assert(rte->rtekind == RTE_RELATION);
tsc = rte->tablesample;
Assert(tsc != NULL);
tsm = GetTsmRoutine(tsc->tsmhandler);
/* Mark the path with the correct row estimate */
if (path->param_info)
path->rows = path->param_info->ppi_rows;
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* Call the sampling method's costing function. */
OidFunctionCall6(tablesample->tsmcost, PointerGetDatum(root),
PointerGetDatum(path), PointerGetDatum(baserel),
PointerGetDatum(tablesample->args),
PointerGetDatum(&pages), PointerGetDatum(&tuples));
/* fetch estimated page cost for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
&spc_seq_page_cost);
spc_page_cost = tablesample->tsmseqscan ? spc_seq_page_cost :
spc_random_page_cost;
/* if NextSampleBlock is used, assume random access, else sequential */
spc_page_cost = (tsm->NextSampleBlock != NULL) ?
spc_random_page_cost : spc_seq_page_cost;
/*
* disk costs
* disk costs (recall that baserel->pages has already been set to the
* number of pages the sampling method will visit)
*/
run_cost += spc_page_cost * pages;
run_cost += spc_page_cost * baserel->pages;
/* CPU costs */
get_restriction_qual_cost(root, baserel, path->param_info, &qpqual_cost);
/*
* CPU costs (recall that baserel->tuples has already been set to the
* number of tuples the sampling method will select). Note that we ignore
* execution cost of the TABLESAMPLE parameter expressions; they will be
* evaluated only once per scan, and in most usages they'll likely be
* simple constants anyway. We also don't charge anything for the
* calculations the sampling method might do internally.
*/
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * tuples;
run_cost += cpu_per_tuple * baserel->tuples;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;