tableam: Provide helper functions for relation sizing.
Most block-based table AMs will need the exact same implementation of the relation_size callback as the heap, and if they use a standard page layout, they will likely need an implementation of the relation_estimate_size callback that is very similar to that of the heap. Rearrange to facilitate code reuse. Patch by me, reviewed by Michael Paquier, Daniel Gustafsson, and Álvaro Herrera. Discussion: http://postgr.es/m/CA+TgmoZ6DBPnP1E-vRpQZUJQijJFD54F+SR_pxGiAAS-MyrigA@mail.gmail.com
This commit is contained in:
parent
482501d433
commit
554106b116
|
@ -19,8 +19,6 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "miscadmin.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
|
@ -37,7 +35,6 @@
|
|||
#include "catalog/storage_xlog.h"
|
||||
#include "commands/progress.h"
|
||||
#include "executor/executor.h"
|
||||
#include "optimizer/plancat.h"
|
||||
#include "pgstat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/bufpage.h"
|
||||
|
@ -1991,26 +1988,6 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
|
|||
* ------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
static uint64
|
||||
heapam_relation_size(Relation rel, ForkNumber forkNumber)
|
||||
{
|
||||
uint64 nblocks = 0;
|
||||
|
||||
/* Open it at the smgr level if not already done */
|
||||
RelationOpenSmgr(rel);
|
||||
|
||||
/* InvalidForkNumber indicates returning the size for all forks */
|
||||
if (forkNumber == InvalidForkNumber)
|
||||
{
|
||||
for (int i = 0; i < MAX_FORKNUM; i++)
|
||||
nblocks += smgrnblocks(rel->rd_smgr, i);
|
||||
}
|
||||
else
|
||||
nblocks = smgrnblocks(rel->rd_smgr, forkNumber);
|
||||
|
||||
return nblocks * BLCKSZ;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check to see whether the table needs a TOAST table. It does only if
|
||||
* (1) there are any toastable attributes, and (2) the maximum length
|
||||
|
@ -2068,106 +2045,20 @@ heapam_relation_needs_toast_table(Relation rel)
|
|||
* ------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
#define HEAP_OVERHEAD_BYTES_PER_TUPLE \
|
||||
(MAXALIGN(SizeofHeapTupleHeader) + sizeof(ItemIdData))
|
||||
#define HEAP_USABLE_BYTES_PER_PAGE \
|
||||
(BLCKSZ - SizeOfPageHeaderData)
|
||||
|
||||
static void
|
||||
heapam_estimate_rel_size(Relation rel, int32 *attr_widths,
|
||||
BlockNumber *pages, double *tuples,
|
||||
double *allvisfrac)
|
||||
{
|
||||
BlockNumber curpages;
|
||||
BlockNumber relpages;
|
||||
double reltuples;
|
||||
BlockNumber relallvisible;
|
||||
double density;
|
||||
|
||||
/* it has storage, ok to call the smgr */
|
||||
curpages = RelationGetNumberOfBlocks(rel);
|
||||
|
||||
/* coerce values in pg_class to more desirable types */
|
||||
relpages = (BlockNumber) rel->rd_rel->relpages;
|
||||
reltuples = (double) rel->rd_rel->reltuples;
|
||||
relallvisible = (BlockNumber) rel->rd_rel->relallvisible;
|
||||
|
||||
/*
|
||||
* HACK: if the relation has never yet been vacuumed, use a minimum size
|
||||
* estimate of 10 pages. The idea here is to avoid assuming a
|
||||
* newly-created table is really small, even if it currently is, because
|
||||
* that may not be true once some data gets loaded into it. Once a vacuum
|
||||
* or analyze cycle has been done on it, it's more reasonable to believe
|
||||
* the size is somewhat stable.
|
||||
*
|
||||
* (Note that this is only an issue if the plan gets cached and used again
|
||||
* after the table has been filled. What we're trying to avoid is using a
|
||||
* nestloop-type plan on a table that has grown substantially since the
|
||||
* plan was made. Normally, autovacuum/autoanalyze will occur once enough
|
||||
* inserts have happened and cause cached-plan invalidation; but that
|
||||
* doesn't happen instantaneously, and it won't happen at all for cases
|
||||
* such as temporary tables.)
|
||||
*
|
||||
* We approximate "never vacuumed" by "has relpages = 0", which means this
|
||||
* will also fire on genuinely empty relations. Not great, but
|
||||
* fortunately that's a seldom-seen case in the real world, and it
|
||||
* shouldn't degrade the quality of the plan too much anyway to err in
|
||||
* this direction.
|
||||
*
|
||||
* If the table has inheritance children, we don't apply this heuristic.
|
||||
* Totally empty parent tables are quite common, so we should be willing
|
||||
* to believe that they are empty.
|
||||
*/
|
||||
if (curpages < 10 &&
|
||||
relpages == 0 &&
|
||||
!rel->rd_rel->relhassubclass)
|
||||
curpages = 10;
|
||||
|
||||
/* report estimated # pages */
|
||||
*pages = curpages;
|
||||
/* quick exit if rel is clearly empty */
|
||||
if (curpages == 0)
|
||||
{
|
||||
*tuples = 0;
|
||||
*allvisfrac = 0;
|
||||
return;
|
||||
}
|
||||
|
||||
/* estimate number of tuples from previous tuple density */
|
||||
if (relpages > 0)
|
||||
density = reltuples / (double) relpages;
|
||||
else
|
||||
{
|
||||
/*
|
||||
* When we have no data because the relation was truncated, estimate
|
||||
* tuple width from attribute datatypes. We assume here that the
|
||||
* pages are completely full, which is OK for tables (since they've
|
||||
* presumably not been VACUUMed yet) but is probably an overestimate
|
||||
* for indexes. Fortunately get_relation_info() can clamp the
|
||||
* overestimate to the parent table's size.
|
||||
*
|
||||
* Note: this code intentionally disregards alignment considerations,
|
||||
* because (a) that would be gilding the lily considering how crude
|
||||
* the estimate is, and (b) it creates platform dependencies in the
|
||||
* default plans which are kind of a headache for regression testing.
|
||||
*/
|
||||
int32 tuple_width;
|
||||
|
||||
tuple_width = get_rel_data_width(rel, attr_widths);
|
||||
tuple_width += MAXALIGN(SizeofHeapTupleHeader);
|
||||
tuple_width += sizeof(ItemIdData);
|
||||
/* note: integer division is intentional here */
|
||||
density = (BLCKSZ - SizeOfPageHeaderData) / tuple_width;
|
||||
}
|
||||
*tuples = rint(density * (double) curpages);
|
||||
|
||||
/*
|
||||
* We use relallvisible as-is, rather than scaling it up like we do for
|
||||
* the pages and tuples counts, on the theory that any pages added since
|
||||
* the last VACUUM are most likely not marked all-visible. But costsize.c
|
||||
* wants it converted to a fraction.
|
||||
*/
|
||||
if (relallvisible == 0 || curpages <= 0)
|
||||
*allvisfrac = 0;
|
||||
else if ((double) relallvisible >= curpages)
|
||||
*allvisfrac = 1;
|
||||
else
|
||||
*allvisfrac = (double) relallvisible / curpages;
|
||||
table_block_relation_estimate_size(rel, attr_widths, pages,
|
||||
tuples, allvisfrac,
|
||||
HEAP_OVERHEAD_BYTES_PER_TUPLE,
|
||||
HEAP_USABLE_BYTES_PER_PAGE);
|
||||
}
|
||||
|
||||
|
||||
|
@ -2644,7 +2535,7 @@ static const TableAmRoutine heapam_methods = {
|
|||
.index_build_range_scan = heapam_index_build_range_scan,
|
||||
.index_validate_scan = heapam_index_validate_scan,
|
||||
|
||||
.relation_size = heapam_relation_size,
|
||||
.relation_size = table_block_relation_size,
|
||||
.relation_needs_toast_table = heapam_relation_needs_toast_table,
|
||||
|
||||
.relation_estimate_size = heapam_estimate_rel_size,
|
||||
|
|
|
@ -19,11 +19,15 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/heapam.h" /* for ss_* */
|
||||
#include "access/tableam.h"
|
||||
#include "access/xact.h"
|
||||
#include "optimizer/plancat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/shmem.h"
|
||||
#include "storage/smgr.h"
|
||||
|
||||
|
||||
/* GUC variables */
|
||||
|
@ -486,3 +490,160 @@ table_block_parallelscan_nextpage(Relation rel, ParallelBlockTableScanDesc pbsca
|
|||
|
||||
return page;
|
||||
}
|
||||
|
||||
/* ----------------------------------------------------------------------------
|
||||
* Helper functions to implement relation sizing for block oriented AMs.
|
||||
* ----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
/*
|
||||
* table_block_relation_size
|
||||
*
|
||||
* If a table AM uses the various relation forks as the sole place where data
|
||||
* is stored, and if it uses them in the expected manner (e.g. the actual data
|
||||
* is in the main fork rather than some other), it can use this implementation
|
||||
* of the relation_size callback rather than implementing its own.
|
||||
*/
|
||||
uint64
|
||||
table_block_relation_size(Relation rel, ForkNumber forkNumber)
|
||||
{
|
||||
uint64 nblocks = 0;
|
||||
|
||||
/* Open it at the smgr level if not already done */
|
||||
RelationOpenSmgr(rel);
|
||||
|
||||
/* InvalidForkNumber indicates returning the size for all forks */
|
||||
if (forkNumber == InvalidForkNumber)
|
||||
{
|
||||
for (int i = 0; i < MAX_FORKNUM; i++)
|
||||
nblocks += smgrnblocks(rel->rd_smgr, i);
|
||||
}
|
||||
else
|
||||
nblocks = smgrnblocks(rel->rd_smgr, forkNumber);
|
||||
|
||||
return nblocks * BLCKSZ;
|
||||
}
|
||||
|
||||
/*
|
||||
* table_block_relation_estimate_size
|
||||
*
|
||||
* This function can't be directly used as the implementation of the
|
||||
* relation_estimate_size callback, because it has a few additional parameters.
|
||||
* Instead, it is intended to be used as a helper function; the caller can
|
||||
* pass through the arguments to its relation_estimate_size function plus the
|
||||
* additional values required here.
|
||||
*
|
||||
* overhead_bytes_per_tuple should contain the approximate number of bytes
|
||||
* of storage required to store a tuple above and beyond what is required for
|
||||
* the tuple data proper. Typically, this would include things like the
|
||||
* size of the tuple header and item pointer. This is only used for query
|
||||
* planning, so a table AM where the value is not constant could choose to
|
||||
* pass a "best guess".
|
||||
*
|
||||
* usable_bytes_per_page should contain the approximate number of bytes per
|
||||
* page usable for tuple data, excluding the page header and any anticipated
|
||||
* special space.
|
||||
*/
|
||||
void
|
||||
table_block_relation_estimate_size(Relation rel, int32 *attr_widths,
|
||||
BlockNumber *pages, double *tuples,
|
||||
double *allvisfrac,
|
||||
Size overhead_bytes_per_tuple,
|
||||
Size usable_bytes_per_page)
|
||||
{
|
||||
BlockNumber curpages;
|
||||
BlockNumber relpages;
|
||||
double reltuples;
|
||||
BlockNumber relallvisible;
|
||||
double density;
|
||||
|
||||
/* it should have storage, so we can call the smgr */
|
||||
curpages = RelationGetNumberOfBlocks(rel);
|
||||
|
||||
/* coerce values in pg_class to more desirable types */
|
||||
relpages = (BlockNumber) rel->rd_rel->relpages;
|
||||
reltuples = (double) rel->rd_rel->reltuples;
|
||||
relallvisible = (BlockNumber) rel->rd_rel->relallvisible;
|
||||
|
||||
/*
|
||||
* HACK: if the relation has never yet been vacuumed, use a minimum size
|
||||
* estimate of 10 pages. The idea here is to avoid assuming a
|
||||
* newly-created table is really small, even if it currently is, because
|
||||
* that may not be true once some data gets loaded into it. Once a vacuum
|
||||
* or analyze cycle has been done on it, it's more reasonable to believe
|
||||
* the size is somewhat stable.
|
||||
*
|
||||
* (Note that this is only an issue if the plan gets cached and used again
|
||||
* after the table has been filled. What we're trying to avoid is using a
|
||||
* nestloop-type plan on a table that has grown substantially since the
|
||||
* plan was made. Normally, autovacuum/autoanalyze will occur once enough
|
||||
* inserts have happened and cause cached-plan invalidation; but that
|
||||
* doesn't happen instantaneously, and it won't happen at all for cases
|
||||
* such as temporary tables.)
|
||||
*
|
||||
* We approximate "never vacuumed" by "has relpages = 0", which means this
|
||||
* will also fire on genuinely empty relations. Not great, but
|
||||
* fortunately that's a seldom-seen case in the real world, and it
|
||||
* shouldn't degrade the quality of the plan too much anyway to err in
|
||||
* this direction.
|
||||
*
|
||||
* If the table has inheritance children, we don't apply this heuristic.
|
||||
* Totally empty parent tables are quite common, so we should be willing
|
||||
* to believe that they are empty.
|
||||
*/
|
||||
if (curpages < 10 &&
|
||||
relpages == 0 &&
|
||||
!rel->rd_rel->relhassubclass)
|
||||
curpages = 10;
|
||||
|
||||
/* report estimated # pages */
|
||||
*pages = curpages;
|
||||
/* quick exit if rel is clearly empty */
|
||||
if (curpages == 0)
|
||||
{
|
||||
*tuples = 0;
|
||||
*allvisfrac = 0;
|
||||
return;
|
||||
}
|
||||
|
||||
/* estimate number of tuples from previous tuple density */
|
||||
if (relpages > 0)
|
||||
density = reltuples / (double) relpages;
|
||||
else
|
||||
{
|
||||
/*
|
||||
* When we have no data because the relation was truncated, estimate
|
||||
* tuple width from attribute datatypes. We assume here that the
|
||||
* pages are completely full, which is OK for tables (since they've
|
||||
* presumably not been VACUUMed yet) but is probably an overestimate
|
||||
* for indexes. Fortunately get_relation_info() can clamp the
|
||||
* overestimate to the parent table's size.
|
||||
*
|
||||
* Note: this code intentionally disregards alignment considerations,
|
||||
* because (a) that would be gilding the lily considering how crude
|
||||
* the estimate is, (b) it creates platform dependencies in the
|
||||
* default plans which are kind of a headache for regression testing,
|
||||
* and (c) different table AMs might use different padding schemes.
|
||||
*/
|
||||
int32 tuple_width;
|
||||
|
||||
tuple_width = get_rel_data_width(rel, attr_widths);
|
||||
tuple_width += overhead_bytes_per_tuple;
|
||||
/* note: integer division is intentional here */
|
||||
density = usable_bytes_per_page / tuple_width;
|
||||
}
|
||||
*tuples = rint(density * (double) curpages);
|
||||
|
||||
/*
|
||||
* We use relallvisible as-is, rather than scaling it up like we do for
|
||||
* the pages and tuples counts, on the theory that any pages added since
|
||||
* the last VACUUM are most likely not marked all-visible. But costsize.c
|
||||
* wants it converted to a fraction.
|
||||
*/
|
||||
if (relallvisible == 0 || curpages <= 0)
|
||||
*allvisfrac = 0;
|
||||
else if ((double) relallvisible >= curpages)
|
||||
*allvisfrac = 1;
|
||||
else
|
||||
*allvisfrac = (double) relallvisible / curpages;
|
||||
}
|
||||
|
|
|
@ -1727,6 +1727,20 @@ extern void table_block_parallelscan_startblock_init(Relation rel,
|
|||
ParallelBlockTableScanDesc pbscan);
|
||||
|
||||
|
||||
/* ----------------------------------------------------------------------------
|
||||
* Helper functions to implement relation sizing for block oriented AMs.
|
||||
* ----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
extern uint64 table_block_relation_size(Relation rel, ForkNumber forkNumber);
|
||||
extern void table_block_relation_estimate_size(Relation rel,
|
||||
int32 *attr_widths,
|
||||
BlockNumber *pages,
|
||||
double *tuples,
|
||||
double *allvisfrac,
|
||||
Size overhead_bytes_per_tuple,
|
||||
Size usable_bytes_per_page);
|
||||
|
||||
/* ----------------------------------------------------------------------------
|
||||
* Functions in tableamapi.c
|
||||
* ----------------------------------------------------------------------------
|
||||
|
|
Loading…
Reference in New Issue