Header And Logo
|
#include "postgres.h"#include <math.h>#include "access/multixact.h"#include "access/transam.h"#include "access/tupconvert.h"#include "access/tuptoaster.h"#include "access/visibilitymap.h"#include "access/xact.h"#include "catalog/index.h"#include "catalog/indexing.h"#include "catalog/pg_collation.h"#include "catalog/pg_inherits_fn.h"#include "catalog/pg_namespace.h"#include "commands/dbcommands.h"#include "commands/tablecmds.h"#include "commands/vacuum.h"#include "executor/executor.h"#include "foreign/fdwapi.h"#include "miscadmin.h"#include "nodes/nodeFuncs.h"#include "parser/parse_oper.h"#include "parser/parse_relation.h"#include "pgstat.h"#include "postmaster/autovacuum.h"#include "storage/bufmgr.h"#include "storage/lmgr.h"#include "storage/proc.h"#include "storage/procarray.h"#include "utils/acl.h"#include "utils/attoptcache.h"#include "utils/datum.h"#include "utils/guc.h"#include "utils/lsyscache.h"#include "utils/memutils.h"#include "utils/pg_rusage.h"#include "utils/sortsupport.h"#include "utils/syscache.h"#include "utils/timestamp.h"#include "utils/tqual.h"
Go to the source code of this file.
Data Structures | |
| struct | BlockSamplerData |
| struct | AnlIndexData |
| struct | StdAnalyzeData |
| struct | ScalarItem |
| struct | ScalarMCVItem |
| struct | CompareScalarsContext |
Defines | |
| #define | WIDTH_THRESHOLD 1024 |
| #define | swapInt(a, b) do {int _tmp; _tmp=a; a=b; b=_tmp;} while(0) |
| #define | swapDatum(a, b) do {Datum _tmp; _tmp=a; a=b; b=_tmp;} while(0) |
Typedefs | |
| typedef BlockSamplerData * | BlockSampler |
| typedef struct AnlIndexData | AnlIndexData |
Functions | |
| static void | do_analyze_rel (Relation onerel, VacuumStmt *vacstmt, AcquireSampleRowsFunc acquirefunc, BlockNumber relpages, bool inh, int elevel) |
| static void | BlockSampler_Init (BlockSampler bs, BlockNumber nblocks, int samplesize) |
| static bool | BlockSampler_HasMore (BlockSampler bs) |
| static BlockNumber | BlockSampler_Next (BlockSampler bs) |
| static void | compute_index_stats (Relation onerel, double totalrows, AnlIndexData *indexdata, int nindexes, HeapTuple *rows, int numrows, MemoryContext col_context) |
| static VacAttrStats * | examine_attribute (Relation onerel, int attnum, Node *index_expr) |
| static int | acquire_sample_rows (Relation onerel, int elevel, HeapTuple *rows, int targrows, double *totalrows, double *totaldeadrows) |
| static int | compare_rows (const void *a, const void *b) |
| static int | acquire_inherited_sample_rows (Relation onerel, int elevel, HeapTuple *rows, int targrows, double *totalrows, double *totaldeadrows) |
| static void | update_attstats (Oid relid, bool inh, int natts, VacAttrStats **vacattrstats) |
| static Datum | std_fetch_func (VacAttrStatsP stats, int rownum, bool *isNull) |
| static Datum | ind_fetch_func (VacAttrStatsP stats, int rownum, bool *isNull) |
| void | analyze_rel (Oid relid, VacuumStmt *vacstmt, BufferAccessStrategy bstrategy) |
| double | anl_random_fract (void) |
| double | anl_init_selection_state (int n) |
| double | anl_get_next_S (double t, int n, double *stateptr) |
| static void | compute_minimal_stats (VacAttrStatsP stats, AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows) |
| static void | compute_scalar_stats (VacAttrStatsP stats, AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows) |
| static int | compare_scalars (const void *a, const void *b, void *arg) |
| static int | compare_mcvs (const void *a, const void *b) |
| bool | std_typanalyze (VacAttrStats *stats) |
Variables | |
| int | default_statistics_target = 100 |
| static MemoryContext | anl_context = NULL |
| static BufferAccessStrategy | vac_strategy |
| #define swapDatum | ( | a, | ||
| b | ||||
| ) | do {Datum _tmp; _tmp=a; a=b; b=_tmp;} while(0) |
Definition at line 1801 of file analyze.c.
Referenced by compute_minimal_stats().
| #define swapInt | ( | a, | ||
| b | ||||
| ) | do {int _tmp; _tmp=a; a=b; b=_tmp;} while(0) |
Definition at line 1800 of file analyze.c.
Referenced by compute_minimal_stats().
| #define WIDTH_THRESHOLD 1024 |
Definition at line 1798 of file analyze.c.
Referenced by compute_minimal_stats(), and compute_scalar_stats().
| typedef struct AnlIndexData AnlIndexData |
| typedef BlockSamplerData* BlockSampler |
| static int acquire_inherited_sample_rows | ( | Relation | onerel, | |
| int | elevel, | |||
| HeapTuple * | rows, | |||
| int | targrows, | |||
| double * | totalrows, | |||
| double * | totaldeadrows | |||
| ) | [static] |
Definition at line 1447 of file analyze.c.
References AccessShareLock, acquire_sample_rows(), Assert, CommandCounterIncrement(), convert_tuples_by_name(), do_convert_tuple(), equalTupleDescs(), find_all_inheritors(), free_conversion_map(), gettext_noop, heap_close, heap_freetuple(), heap_open(), i, lfirst_oid, list_length(), Min, NoLock, NULL, palloc(), RELATION_IS_OTHER_TEMP, RelationGetDescr, RelationGetNumberOfBlocks, RelationGetRelid, rint(), and SetRelationHasSubclass().
Referenced by do_analyze_rel().
{
List *tableOIDs;
Relation *rels;
double *relblocks;
double totalblocks;
int numrows,
nrels,
i;
ListCell *lc;
/*
* Find all members of inheritance set. We only need AccessShareLock on
* the children.
*/
tableOIDs =
find_all_inheritors(RelationGetRelid(onerel), AccessShareLock, NULL);
/*
* Check that there's at least one descendant, else fail. This could
* happen despite analyze_rel's relhassubclass check, if table once had a
* child but no longer does. In that case, we can clear the
* relhassubclass field so as not to make the same mistake again later.
* (This is safe because we hold ShareUpdateExclusiveLock.)
*/
if (list_length(tableOIDs) < 2)
{
/* CCI because we already updated the pg_class row in this command */
CommandCounterIncrement();
SetRelationHasSubclass(RelationGetRelid(onerel), false);
return 0;
}
/*
* Count the blocks in all the relations. The result could overflow
* BlockNumber, so we use double arithmetic.
*/
rels = (Relation *) palloc(list_length(tableOIDs) * sizeof(Relation));
relblocks = (double *) palloc(list_length(tableOIDs) * sizeof(double));
totalblocks = 0;
nrels = 0;
foreach(lc, tableOIDs)
{
Oid childOID = lfirst_oid(lc);
Relation childrel;
/* We already got the needed lock */
childrel = heap_open(childOID, NoLock);
/* Ignore if temp table of another backend */
if (RELATION_IS_OTHER_TEMP(childrel))
{
/* ... but release the lock on it */
Assert(childrel != onerel);
heap_close(childrel, AccessShareLock);
continue;
}
rels[nrels] = childrel;
relblocks[nrels] = (double) RelationGetNumberOfBlocks(childrel);
totalblocks += relblocks[nrels];
nrels++;
}
/*
* Now sample rows from each relation, proportionally to its fraction of
* the total block count. (This might be less than desirable if the child
* rels have radically different free-space percentages, but it's not
* clear that it's worth working harder.)
*/
numrows = 0;
*totalrows = 0;
*totaldeadrows = 0;
for (i = 0; i < nrels; i++)
{
Relation childrel = rels[i];
double childblocks = relblocks[i];
if (childblocks > 0)
{
int childtargrows;
childtargrows = (int) rint(targrows * childblocks / totalblocks);
/* Make sure we don't overrun due to roundoff error */
childtargrows = Min(childtargrows, targrows - numrows);
if (childtargrows > 0)
{
int childrows;
double trows,
tdrows;
/* Fetch a random sample of the child's rows */
childrows = acquire_sample_rows(childrel,
elevel,
rows + numrows,
childtargrows,
&trows,
&tdrows);
/* We may need to convert from child's rowtype to parent's */
if (childrows > 0 &&
!equalTupleDescs(RelationGetDescr(childrel),
RelationGetDescr(onerel)))
{
TupleConversionMap *map;
map = convert_tuples_by_name(RelationGetDescr(childrel),
RelationGetDescr(onerel),
gettext_noop("could not convert row type"));
if (map != NULL)
{
int j;
for (j = 0; j < childrows; j++)
{
HeapTuple newtup;
newtup = do_convert_tuple(rows[numrows + j], map);
heap_freetuple(rows[numrows + j]);
rows[numrows + j] = newtup;
}
free_conversion_map(map);
}
}
/* And add to counts */
numrows += childrows;
*totalrows += trows;
*totaldeadrows += tdrows;
}
}
/*
* Note: we cannot release the child-table locks, since we may have
* pointers to their TOAST tables in the sampled rows.
*/
heap_close(childrel, NoLock);
}
return numrows;
}
| static int acquire_sample_rows | ( | Relation | onerel, | |
| int | elevel, | |||
| HeapTuple * | rows, | |||
| int | targrows, | |||
| double * | totalrows, | |||
| double * | totaldeadrows | |||
| ) | [static] |
Definition at line 1065 of file analyze.c.
References anl_get_next_S(), anl_init_selection_state(), anl_random_fract(), Assert, BlockSampler_HasMore(), BlockSampler_Init(), BlockSampler_Next(), BUFFER_LOCK_SHARE, BufferGetPage, compare_rows(), elog, ereport, errmsg(), ERROR, FirstOffsetNumber, GetOldestXmin(), heap_copytuple(), heap_freetuple(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleSatisfiesVacuum(), ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemPointerSet, LockBuffer(), BlockSamplerData::m, MAIN_FORKNUM, OldestXmin, PageGetItem, PageGetItemId, PageGetMaxOffsetNumber, qsort, RBM_NORMAL, RelationData::rd_rel, ReadBufferExtended(), RelationGetNumberOfBlocks, RelationGetRelationName, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, TransactionIdIsCurrentTransactionId(), UnlockReleaseBuffer(), vac_estimate_reltuples(), and vacuum_delay_point().
Referenced by acquire_inherited_sample_rows().
{
int numrows = 0; /* # rows now in reservoir */
double samplerows = 0; /* total # rows collected */
double liverows = 0; /* # live rows seen */
double deadrows = 0; /* # dead rows seen */
double rowstoskip = -1; /* -1 means not set yet */
BlockNumber totalblocks;
TransactionId OldestXmin;
BlockSamplerData bs;
double rstate;
Assert(targrows > 0);
totalblocks = RelationGetNumberOfBlocks(onerel);
/* Need a cutoff xmin for HeapTupleSatisfiesVacuum */
OldestXmin = GetOldestXmin(onerel->rd_rel->relisshared, true);
/* Prepare for sampling block numbers */
BlockSampler_Init(&bs, totalblocks, targrows);
/* Prepare for sampling rows */
rstate = anl_init_selection_state(targrows);
/* Outer loop over blocks to sample */
while (BlockSampler_HasMore(&bs))
{
BlockNumber targblock = BlockSampler_Next(&bs);
Buffer targbuffer;
Page targpage;
OffsetNumber targoffset,
maxoffset;
vacuum_delay_point();
/*
* We must maintain a pin on the target page's buffer to ensure that
* the maxoffset value stays good (else concurrent VACUUM might delete
* tuples out from under us). Hence, pin the page until we are done
* looking at it. We also choose to hold sharelock on the buffer
* throughout --- we could release and re-acquire sharelock for each
* tuple, but since we aren't doing much work per tuple, the extra
* lock traffic is probably better avoided.
*/
targbuffer = ReadBufferExtended(onerel, MAIN_FORKNUM, targblock,
RBM_NORMAL, vac_strategy);
LockBuffer(targbuffer, BUFFER_LOCK_SHARE);
targpage = BufferGetPage(targbuffer);
maxoffset = PageGetMaxOffsetNumber(targpage);
/* Inner loop over all tuples on the selected page */
for (targoffset = FirstOffsetNumber; targoffset <= maxoffset; targoffset++)
{
ItemId itemid;
HeapTupleData targtuple;
bool sample_it = false;
itemid = PageGetItemId(targpage, targoffset);
/*
* We ignore unused and redirect line pointers. DEAD line
* pointers should be counted as dead, because we need vacuum to
* run to get rid of them. Note that this rule agrees with the
* way that heap_page_prune() counts things.
*/
if (!ItemIdIsNormal(itemid))
{
if (ItemIdIsDead(itemid))
deadrows += 1;
continue;
}
ItemPointerSet(&targtuple.t_self, targblock, targoffset);
targtuple.t_data = (HeapTupleHeader) PageGetItem(targpage, itemid);
targtuple.t_len = ItemIdGetLength(itemid);
switch (HeapTupleSatisfiesVacuum(targtuple.t_data,
OldestXmin,
targbuffer))
{
case HEAPTUPLE_LIVE:
sample_it = true;
liverows += 1;
break;
case HEAPTUPLE_DEAD:
case HEAPTUPLE_RECENTLY_DEAD:
/* Count dead and recently-dead rows */
deadrows += 1;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* Insert-in-progress rows are not counted. We assume
* that when the inserting transaction commits or aborts,
* it will send a stats message to increment the proper
* count. This works right only if that transaction ends
* after we finish analyzing the table; if things happen
* in the other order, its stats update will be
* overwritten by ours. However, the error will be large
* only if the other transaction runs long enough to
* insert many tuples, so assuming it will finish after us
* is the safer option.
*
* A special case is that the inserting transaction might
* be our own. In this case we should count and sample
* the row, to accommodate users who load a table and
* analyze it in one transaction. (pgstat_report_analyze
* has to adjust the numbers we send to the stats
* collector to make this come out right.)
*/
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(targtuple.t_data)))
{
sample_it = true;
liverows += 1;
}
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* We count delete-in-progress rows as still live, using
* the same reasoning given above; but we don't bother to
* include them in the sample.
*
* If the delete was done by our own transaction, however,
* we must count the row as dead to make
* pgstat_report_analyze's stats adjustments come out
* right. (Note: this works out properly when the row was
* both inserted and deleted in our xact.)
*/
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(targtuple.t_data)))
deadrows += 1;
else
liverows += 1;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (sample_it)
{
/*
* The first targrows sample rows are simply copied into the
* reservoir. Then we start replacing tuples in the sample
* until we reach the end of the relation. This algorithm is
* from Jeff Vitter's paper (see full citation below). It
* works by repeatedly computing the number of tuples to skip
* before selecting a tuple, which replaces a randomly chosen
* element of the reservoir (current set of tuples). At all
* times the reservoir is a true random sample of the tuples
* we've passed over so far, so when we fall off the end of
* the relation we're done.
*/
if (numrows < targrows)
rows[numrows++] = heap_copytuple(&targtuple);
else
{
/*
* t in Vitter's paper is the number of records already
* processed. If we need to compute a new S value, we
* must use the not-yet-incremented value of samplerows as
* t.
*/
if (rowstoskip < 0)
rowstoskip = anl_get_next_S(samplerows, targrows,
&rstate);
if (rowstoskip <= 0)
{
/*
* Found a suitable tuple, so save it, replacing one
* old tuple at random
*/
int k = (int) (targrows * anl_random_fract());
Assert(k >= 0 && k < targrows);
heap_freetuple(rows[k]);
rows[k] = heap_copytuple(&targtuple);
}
rowstoskip -= 1;
}
samplerows += 1;
}
}
/* Now release the lock and pin on the page */
UnlockReleaseBuffer(targbuffer);
}
/*
* If we didn't find as many tuples as we wanted then we're done. No sort
* is needed, since they're already in order.
*
* Otherwise we need to sort the collected tuples by position
* (itempointer). It's not worth worrying about corner cases where the
* tuples are already sorted.
*/
if (numrows == targrows)
qsort((void *) rows, numrows, sizeof(HeapTuple), compare_rows);
/*
* Estimate total numbers of rows in relation. For live rows, use
* vac_estimate_reltuples; for dead rows, we have no source of old
* information, so we have to assume the density is the same in unseen
* pages as in the pages we scanned.
*/
*totalrows = vac_estimate_reltuples(onerel, true,
totalblocks,
bs.m,
liverows);
if (bs.m > 0)
*totaldeadrows = floor((deadrows / bs.m) * totalblocks + 0.5);
else
*totaldeadrows = 0.0;
/*
* Emit some interesting relation info
*/
ereport(elevel,
(errmsg("\"%s\": scanned %d of %u pages, "
"containing %.0f live rows and %.0f dead rows; "
"%d rows in sample, %.0f estimated total rows",
RelationGetRelationName(onerel),
bs.m, totalblocks,
liverows, deadrows,
numrows, *totalrows)));
return numrows;
}
| void analyze_rel | ( | Oid | relid, | |
| VacuumStmt * | vacstmt, | |||
| BufferAccessStrategy | bstrategy | |||
| ) |
Definition at line 117 of file analyze.c.
References FdwRoutine::AnalyzeForeignTable, CHECK_FOR_INTERRUPTS, ConditionalLockRelationOid(), do_analyze_rel(), elevel, ereport, errcode(), errmsg(), GetFdwRoutineForRelation(), GetUserId(), IsAutoVacuumWorkerProcess(), LOG, Log_autovacuum_min_duration, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MyDatabaseId, MyPgXact, NoLock, NULL, VacuumStmt::options, PG_CATALOG_NAMESPACE, pg_class_ownercheck(), pg_database_ownercheck(), ProcArrayLock, RelationData::rd_rel, VacuumStmt::relation, relation_close(), RELATION_IS_OTHER_TEMP, RelationGetNumberOfBlocks, RelationGetRelationName, RelationGetRelid, RELKIND_FOREIGN_TABLE, RELKIND_MATVIEW, RELKIND_RELATION, RangeVar::relname, ShareUpdateExclusiveLock, StatisticRelationId, try_relation_open(), VACOPT_NOWAIT, VACOPT_VACUUM, VACOPT_VERBOSE, PGXACT::vacuumFlags, and WARNING.
Referenced by vacuum().
{
Relation onerel;
int elevel;
AcquireSampleRowsFunc acquirefunc = NULL;
BlockNumber relpages = 0;
/* Select logging level */
if (vacstmt->options & VACOPT_VERBOSE)
elevel = INFO;
else
elevel = DEBUG2;
/* Set up static variables */
vac_strategy = bstrategy;
/*
* Check for user-requested abort.
*/
CHECK_FOR_INTERRUPTS();
/*
* Open the relation, getting ShareUpdateExclusiveLock to ensure that two
* ANALYZEs don't run on it concurrently. (This also locks out a
* concurrent VACUUM, which doesn't matter much at the moment but might
* matter if we ever try to accumulate stats on dead tuples.) If the rel
* has been dropped since we last saw it, we don't need to process it.
*/
if (!(vacstmt->options & VACOPT_NOWAIT))
onerel = try_relation_open(relid, ShareUpdateExclusiveLock);
else if (ConditionalLockRelationOid(relid, ShareUpdateExclusiveLock))
onerel = try_relation_open(relid, NoLock);
else
{
onerel = NULL;
if (IsAutoVacuumWorkerProcess() && Log_autovacuum_min_duration >= 0)
ereport(LOG,
(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
errmsg("skipping analyze of \"%s\" --- lock not available",
vacstmt->relation->relname)));
}
if (!onerel)
return;
/*
* Check permissions --- this should match vacuum's check!
*/
if (!(pg_class_ownercheck(RelationGetRelid(onerel), GetUserId()) ||
(pg_database_ownercheck(MyDatabaseId, GetUserId()) && !onerel->rd_rel->relisshared)))
{
/* No need for a WARNING if we already complained during VACUUM */
if (!(vacstmt->options & VACOPT_VACUUM))
{
if (onerel->rd_rel->relisshared)
ereport(WARNING,
(errmsg("skipping \"%s\" --- only superuser can analyze it",
RelationGetRelationName(onerel))));
else if (onerel->rd_rel->relnamespace == PG_CATALOG_NAMESPACE)
ereport(WARNING,
(errmsg("skipping \"%s\" --- only superuser or database owner can analyze it",
RelationGetRelationName(onerel))));
else
ereport(WARNING,
(errmsg("skipping \"%s\" --- only table or database owner can analyze it",
RelationGetRelationName(onerel))));
}
relation_close(onerel, ShareUpdateExclusiveLock);
return;
}
/*
* Silently ignore tables that are temp tables of other backends ---
* trying to analyze these is rather pointless, since their contents are
* probably not up-to-date on disk. (We don't throw a warning here; it
* would just lead to chatter during a database-wide ANALYZE.)
*/
if (RELATION_IS_OTHER_TEMP(onerel))
{
relation_close(onerel, ShareUpdateExclusiveLock);
return;
}
/*
* We can ANALYZE any table except pg_statistic. See update_attstats
*/
if (RelationGetRelid(onerel) == StatisticRelationId)
{
relation_close(onerel, ShareUpdateExclusiveLock);
return;
}
/*
* Check that it's a plain table, materialized view, or foreign table; we
* used to do this in get_rel_oids() but seems safer to check after we've
* locked the relation.
*/
if (onerel->rd_rel->relkind == RELKIND_RELATION ||
onerel->rd_rel->relkind == RELKIND_MATVIEW)
{
/* Regular table, so we'll use the regular row acquisition function */
acquirefunc = acquire_sample_rows;
/* Also get regular table's size */
relpages = RelationGetNumberOfBlocks(onerel);
}
else if (onerel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
{
/*
* For a foreign table, call the FDW's hook function to see whether it
* supports analysis.
*/
FdwRoutine *fdwroutine;
bool ok = false;
fdwroutine = GetFdwRoutineForRelation(onerel, false);
if (fdwroutine->AnalyzeForeignTable != NULL)
ok = fdwroutine->AnalyzeForeignTable(onerel,
&acquirefunc,
&relpages);
if (!ok)
{
ereport(WARNING,
(errmsg("skipping \"%s\" --- cannot analyze this foreign table",
RelationGetRelationName(onerel))));
relation_close(onerel, ShareUpdateExclusiveLock);
return;
}
}
else
{
/* No need for a WARNING if we already complained during VACUUM */
if (!(vacstmt->options & VACOPT_VACUUM))
ereport(WARNING,
(errmsg("skipping \"%s\" --- cannot analyze non-tables or special system tables",
RelationGetRelationName(onerel))));
relation_close(onerel, ShareUpdateExclusiveLock);
return;
}
/*
* OK, let's do it. First let other backends know I'm in ANALYZE.
*/
LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
MyPgXact->vacuumFlags |= PROC_IN_ANALYZE;
LWLockRelease(ProcArrayLock);
/*
* Do the normal non-recursive ANALYZE.
*/
do_analyze_rel(onerel, vacstmt, acquirefunc, relpages, false, elevel);
/*
* If there are child tables, do recursive ANALYZE.
*/
if (onerel->rd_rel->relhassubclass)
do_analyze_rel(onerel, vacstmt, acquirefunc, relpages, true, elevel);
/*
* Close source relation now, but keep lock so that no one deletes it
* before we commit. (If someone did, they'd fail to clean up the entries
* we made in pg_statistic. Also, releasing the lock before commit would
* expose us to concurrent-update failures in update_attstats.)
*/
relation_close(onerel, NoLock);
/*
* Reset my PGXACT flag. Note: we need this here, and not in vacuum_rel,
* because the vacuum flag is cleared by the end-of-xact code.
*/
LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
MyPgXact->vacuumFlags &= ~PROC_IN_ANALYZE;
LWLockRelease(ProcArrayLock);
}
| double anl_get_next_S | ( | double | t, | |
| int | n, | |||
| double * | stateptr | |||
| ) |
Definition at line 1333 of file analyze.c.
References anl_random_fract(), and W.
Referenced by acquire_sample_rows(), analyze_row_processor(), and file_acquire_sample_rows().
{
double S;
/* The magic constant here is T from Vitter's paper */
if (t <= (22.0 * n))
{
/* Process records using Algorithm X until t is large enough */
double V,
quot;
V = anl_random_fract(); /* Generate V */
S = 0;
t += 1;
/* Note: "num" in Vitter's code is always equal to t - n */
quot = (t - (double) n) / t;
/* Find min S satisfying (4.1) */
while (quot > V)
{
S += 1;
t += 1;
quot *= (t - (double) n) / t;
}
}
else
{
/* Now apply Algorithm Z */
double W = *stateptr;
double term = t - (double) n + 1;
for (;;)
{
double numer,
numer_lim,
denom;
double U,
X,
lhs,
rhs,
y,
tmp;
/* Generate U and X */
U = anl_random_fract();
X = t * (W - 1.0);
S = floor(X); /* S is tentatively set to floor(X) */
/* Test if U <= h(S)/cg(X) in the manner of (6.3) */
tmp = (t + 1) / term;
lhs = exp(log(((U * tmp * tmp) * (term + S)) / (t + X)) / n);
rhs = (((t + X) / (term + S)) * term) / t;
if (lhs <= rhs)
{
W = rhs / lhs;
break;
}
/* Test if U <= f(S)/cg(X) */
y = (((U * (t + 1)) / term) * (t + S + 1)) / (t + X);
if ((double) n < S)
{
denom = t;
numer_lim = term + S;
}
else
{
denom = t - (double) n + S;
numer_lim = t + 1;
}
for (numer = t + S; numer >= numer_lim; numer -= 1)
{
y *= numer / denom;
denom -= 1;
}
W = exp(-log(anl_random_fract()) / n); /* Generate W in advance */
if (exp(log(y) / n) <= (t + X) / t)
break;
}
*stateptr = W;
}
return S;
}
| double anl_init_selection_state | ( | int | n | ) |
Definition at line 1326 of file analyze.c.
References anl_random_fract().
Referenced by acquire_sample_rows(), file_acquire_sample_rows(), and postgresAcquireSampleRowsFunc().
{
/* Initial value of W (for use when Algorithm Z is first applied) */
return exp(-log(anl_random_fract()) / n);
}
| double anl_random_fract | ( | void | ) |
Definition at line 1306 of file analyze.c.
References MAX_RANDOM_VALUE, and random().
Referenced by acquire_sample_rows(), analyze_row_processor(), anl_get_next_S(), anl_init_selection_state(), BlockSampler_Next(), and file_acquire_sample_rows().
{
return ((double) random() + 1) / ((double) MAX_RANDOM_VALUE + 2);
}
| static bool BlockSampler_HasMore | ( | BlockSampler | bs | ) | [static] |
Definition at line 971 of file analyze.c.
References BlockSamplerData::m, BlockSamplerData::n, BlockSamplerData::N, and BlockSamplerData::t.
Referenced by acquire_sample_rows(), and BlockSampler_Next().
| static void BlockSampler_Init | ( | BlockSampler | bs, | |
| BlockNumber | nblocks, | |||
| int | samplesize | |||
| ) | [static] |
Definition at line 957 of file analyze.c.
References BlockSamplerData::m, BlockSamplerData::n, BlockSamplerData::N, and BlockSamplerData::t.
Referenced by acquire_sample_rows().
| static BlockNumber BlockSampler_Next | ( | BlockSampler | bs | ) | [static] |
Definition at line 977 of file analyze.c.
References anl_random_fract(), Assert, BlockSampler_HasMore(), K, BlockSamplerData::m, BlockSamplerData::n, BlockSamplerData::N, and BlockSamplerData::t.
Referenced by acquire_sample_rows().
{
BlockNumber K = bs->N - bs->t; /* remaining blocks */
int k = bs->n - bs->m; /* blocks still to sample */
double p; /* probability to skip block */
double V; /* random */
Assert(BlockSampler_HasMore(bs)); /* hence K > 0 and k > 0 */
if ((BlockNumber) k >= K)
{
/* need all the rest */
bs->m++;
return bs->t++;
}
/*----------
* It is not obvious that this code matches Knuth's Algorithm S.
* Knuth says to skip the current block with probability 1 - k/K.
* If we are to skip, we should advance t (hence decrease K), and
* repeat the same probabilistic test for the next block. The naive
* implementation thus requires an anl_random_fract() call for each block
* number. But we can reduce this to one anl_random_fract() call per
* selected block, by noting that each time the while-test succeeds,
* we can reinterpret V as a uniform random number in the range 0 to p.
* Therefore, instead of choosing a new V, we just adjust p to be
* the appropriate fraction of its former value, and our next loop
* makes the appropriate probabilistic test.
*
* We have initially K > k > 0. If the loop reduces K to equal k,
* the next while-test must fail since p will become exactly zero
* (we assume there will not be roundoff error in the division).
* (Note: Knuth suggests a "<=" loop condition, but we use "<" just
* to be doubly sure about roundoff error.) Therefore K cannot become
* less than k, which means that we cannot fail to select enough blocks.
*----------
*/
V = anl_random_fract();
p = 1.0 - (double) k / (double) K;
while (V < p)
{
/* skip */
bs->t++;
K--; /* keep K == N - t */
/* adjust p to be new cutoff point in reduced range */
p *= 1.0 - (double) k / (double) K;
}
/* select */
bs->m++;
return bs->t++;
}
| static int compare_mcvs | ( | const void * | a, | |
| const void * | b | |||
| ) | [static] |
Definition at line 2790 of file analyze.c.
Referenced by compute_scalar_stats().
{
int da = ((const ScalarMCVItem *) a)->first;
int db = ((const ScalarMCVItem *) b)->first;
return da - db;
}
| static int compare_rows | ( | const void * | a, | |
| const void * | b | |||
| ) | [static] |
Definition at line 1418 of file analyze.c.
References ItemPointerGetBlockNumber, ItemPointerGetOffsetNumber, and HeapTupleData::t_self.
Referenced by acquire_sample_rows().
{
HeapTuple ha = *(const HeapTuple *) a;
HeapTuple hb = *(const HeapTuple *) b;
BlockNumber ba = ItemPointerGetBlockNumber(&ha->t_self);
OffsetNumber oa = ItemPointerGetOffsetNumber(&ha->t_self);
BlockNumber bb = ItemPointerGetBlockNumber(&hb->t_self);
OffsetNumber ob = ItemPointerGetOffsetNumber(&hb->t_self);
if (ba < bb)
return -1;
if (ba > bb)
return 1;
if (oa < ob)
return -1;
if (oa > ob)
return 1;
return 0;
}
| static int compare_scalars | ( | const void * | a, | |
| const void * | b, | |||
| void * | arg | |||
| ) | [static] |
Definition at line 2759 of file analyze.c.
References ApplySortComparator(), CompareScalarsContext::ssup, and CompareScalarsContext::tupnoLink.
Referenced by compute_scalar_stats().
{
Datum da = ((const ScalarItem *) a)->value;
int ta = ((const ScalarItem *) a)->tupno;
Datum db = ((const ScalarItem *) b)->value;
int tb = ((const ScalarItem *) b)->tupno;
CompareScalarsContext *cxt = (CompareScalarsContext *) arg;
int compare;
compare = ApplySortComparator(da, false, db, false, cxt->ssup);
if (compare != 0)
return compare;
/*
* The two datums are equal, so update cxt->tupnoLink[].
*/
if (cxt->tupnoLink[ta] < tb)
cxt->tupnoLink[ta] = tb;
if (cxt->tupnoLink[tb] < ta)
cxt->tupnoLink[tb] = ta;
/*
* For equal datums, sort by tupno
*/
return ta - tb;
}
| static void compute_index_stats | ( | Relation | onerel, | |
| double | totalrows, | |||
| AnlIndexData * | indexdata, | |||
| int | nindexes, | |||
| HeapTuple * | rows, | |||
| int | numrows, | |||
| MemoryContext | col_context | |||
| ) | [static] |
Definition at line 674 of file analyze.c.
References ALLOCSET_DEFAULT_INITSIZE, ALLOCSET_DEFAULT_MAXSIZE, ALLOCSET_DEFAULT_MINSIZE, AllocSetContextCreate(), VacAttrStats::attr, AnlIndexData::attr_cnt, VacAttrStats::attrtype, VacAttrStats::compute_stats, CreateExecutorState(), datumCopy(), ExprContext::ecxt_scantuple, ExecDropSingleTupleTableSlot(), ExecPrepareExpr(), ExecQual(), ExecStoreTuple(), VacAttrStats::exprnulls, VacAttrStats::exprvals, FormIndexDatum(), FreeExecutorState(), get_attribute_options(), GetPerTupleExprContext, i, IndexInfo::ii_Predicate, ind_fetch_func(), AnlIndexData::indexInfo, InvalidBuffer, MakeSingleTupleTableSlot(), MemoryContextDelete(), MemoryContextResetAndDeleteChildren(), MemoryContextSwitchTo(), AttributeOpts::n_distinct, NIL, NULL, palloc(), RelationGetDescr, ResetExprContext, VacAttrStats::rowstride, VacAttrStats::stadistinct, AnlIndexData::tupleFract, AnlIndexData::vacattrstats, and values.
Referenced by do_analyze_rel().
{
MemoryContext ind_context,
old_context;
Datum values[INDEX_MAX_KEYS];
bool isnull[INDEX_MAX_KEYS];
int ind,
i;
ind_context = AllocSetContextCreate(anl_context,
"Analyze Index",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
old_context = MemoryContextSwitchTo(ind_context);
for (ind = 0; ind < nindexes; ind++)
{
AnlIndexData *thisdata = &indexdata[ind];
IndexInfo *indexInfo = thisdata->indexInfo;
int attr_cnt = thisdata->attr_cnt;
TupleTableSlot *slot;
EState *estate;
ExprContext *econtext;
List *predicate;
Datum *exprvals;
bool *exprnulls;
int numindexrows,
tcnt,
rowno;
double totalindexrows;
/* Ignore index if no columns to analyze and not partial */
if (attr_cnt == 0 && indexInfo->ii_Predicate == NIL)
continue;
/*
* Need an EState for evaluation of index expressions and
* partial-index predicates. Create it in the per-index context to be
* sure it gets cleaned up at the bottom of the loop.
*/
estate = CreateExecutorState();
econtext = GetPerTupleExprContext(estate);
/* Need a slot to hold the current heap tuple, too */
slot = MakeSingleTupleTableSlot(RelationGetDescr(onerel));
/* Arrange for econtext's scan tuple to be the tuple under test */
econtext->ecxt_scantuple = slot;
/* Set up execution state for predicate. */
predicate = (List *)
ExecPrepareExpr((Expr *) indexInfo->ii_Predicate,
estate);
/* Compute and save index expression values */
exprvals = (Datum *) palloc(numrows * attr_cnt * sizeof(Datum));
exprnulls = (bool *) palloc(numrows * attr_cnt * sizeof(bool));
numindexrows = 0;
tcnt = 0;
for (rowno = 0; rowno < numrows; rowno++)
{
HeapTuple heapTuple = rows[rowno];
/*
* Reset the per-tuple context each time, to reclaim any cruft
* left behind by evaluating the predicate or index expressions.
*/
ResetExprContext(econtext);
/* Set up for predicate or expression evaluation */
ExecStoreTuple(heapTuple, slot, InvalidBuffer, false);
/* If index is partial, check predicate */
if (predicate != NIL)
{
if (!ExecQual(predicate, econtext, false))
continue;
}
numindexrows++;
if (attr_cnt > 0)
{
/*
* Evaluate the index row to compute expression values. We
* could do this by hand, but FormIndexDatum is convenient.
*/
FormIndexDatum(indexInfo,
slot,
estate,
values,
isnull);
/*
* Save just the columns we care about. We copy the values
* into ind_context from the estate's per-tuple context.
*/
for (i = 0; i < attr_cnt; i++)
{
VacAttrStats *stats = thisdata->vacattrstats[i];
int attnum = stats->attr->attnum;
if (isnull[attnum - 1])
{
exprvals[tcnt] = (Datum) 0;
exprnulls[tcnt] = true;
}
else
{
exprvals[tcnt] = datumCopy(values[attnum - 1],
stats->attrtype->typbyval,
stats->attrtype->typlen);
exprnulls[tcnt] = false;
}
tcnt++;
}
}
}
/*
* Having counted the number of rows that pass the predicate in the
* sample, we can estimate the total number of rows in the index.
*/
thisdata->tupleFract = (double) numindexrows / (double) numrows;
totalindexrows = ceil(thisdata->tupleFract * totalrows);
/*
* Now we can compute the statistics for the expression columns.
*/
if (numindexrows > 0)
{
MemoryContextSwitchTo(col_context);
for (i = 0; i < attr_cnt; i++)
{
VacAttrStats *stats = thisdata->vacattrstats[i];
AttributeOpts *aopt =
get_attribute_options(stats->attr->attrelid,
stats->attr->attnum);
stats->exprvals = exprvals + i;
stats->exprnulls = exprnulls + i;
stats->rowstride = attr_cnt;
(*stats->compute_stats) (stats,
ind_fetch_func,
numindexrows,
totalindexrows);
/*
* If the n_distinct option is specified, it overrides the
* above computation. For indices, we always use just
* n_distinct, not n_distinct_inherited.
*/
if (aopt != NULL && aopt->n_distinct != 0.0)
stats->stadistinct = aopt->n_distinct;
MemoryContextResetAndDeleteChildren(col_context);
}
}
/* And clean up */
MemoryContextSwitchTo(ind_context);
ExecDropSingleTupleTableSlot(slot);
FreeExecutorState(estate);
MemoryContextResetAndDeleteChildren(ind_context);
}
MemoryContextSwitchTo(old_context);
MemoryContextDelete(ind_context);
}
| static void compute_minimal_stats | ( | VacAttrStatsP | stats, | |
| AnalyzeAttrFetchFunc | fetchfunc, | |||
| int | samplerows, | |||
| double | totalrows | |||
| ) | [static] |
Definition at line 1932 of file analyze.c.
References VacAttrStats::anl_context, VacAttrStats::attr, VacAttrStats::attrtype, datumCopy(), DatumGetBool, DatumGetCString, DatumGetPointer, DEFAULT_COLLATION_OID, StdAnalyzeData::eqfunc, StdAnalyzeData::eqopr, VacAttrStats::extra_data, fmgr_info(), FunctionCall2Coll(), i, MemoryContextSwitchTo(), VacAttrStats::numnumbers, VacAttrStats::numvalues, palloc(), PG_DETOAST_DATUM, PointerGetDatum, VacAttrStats::stadistinct, VacAttrStats::stakind, VacAttrStats::stanullfrac, VacAttrStats::stanumbers, VacAttrStats::staop, VacAttrStats::stats_valid, VacAttrStats::stavalues, VacAttrStats::stawidth, swapDatum, swapInt, toast_raw_datum_size(), vacuum_delay_point(), value, VARSIZE_ANY, and WIDTH_THRESHOLD.
{
int i;
int null_cnt = 0;
int nonnull_cnt = 0;
int toowide_cnt = 0;
double total_width = 0;
bool is_varlena = (!stats->attrtype->typbyval &&
stats->attrtype->typlen == -1);
bool is_varwidth = (!stats->attrtype->typbyval &&
stats->attrtype->typlen < 0);
FmgrInfo f_cmpeq;
typedef struct
{
Datum value;
int count;
} TrackItem;
TrackItem *track;
int track_cnt,
track_max;
int num_mcv = stats->attr->attstattarget;
StdAnalyzeData *mystats = (StdAnalyzeData *) stats->extra_data;
/*
* We track up to 2*n values for an n-element MCV list; but at least 10
*/
track_max = 2 * num_mcv;
if (track_max < 10)
track_max = 10;
track = (TrackItem *) palloc(track_max * sizeof(TrackItem));
track_cnt = 0;
fmgr_info(mystats->eqfunc, &f_cmpeq);
for (i = 0; i < samplerows; i++)
{
Datum value;
bool isnull;
bool match;
int firstcount1,
j;
vacuum_delay_point();
value = fetchfunc(stats, i, &isnull);
/* Check for null/nonnull */
if (isnull)
{
null_cnt++;
continue;
}
nonnull_cnt++;
/*
* If it's a variable-width field, add up widths for average width
* calculation. Note that if the value is toasted, we use the toasted
* width. We don't bother with this calculation if it's a fixed-width
* type.
*/
if (is_varlena)
{
total_width += VARSIZE_ANY(DatumGetPointer(value));
/*
* If the value is toasted, we want to detoast it just once to
* avoid repeated detoastings and resultant excess memory usage
* during the comparisons. Also, check to see if the value is
* excessively wide, and if so don't detoast at all --- just
* ignore the value.
*/
if (toast_raw_datum_size(value) > WIDTH_THRESHOLD)
{
toowide_cnt++;
continue;
}
value = PointerGetDatum(PG_DETOAST_DATUM(value));
}
else if (is_varwidth)
{
/* must be cstring */
total_width += strlen(DatumGetCString(value)) + 1;
}
/*
* See if the value matches anything we're already tracking.
*/
match = false;
firstcount1 = track_cnt;
for (j = 0; j < track_cnt; j++)
{
/* We always use the default collation for statistics */
if (DatumGetBool(FunctionCall2Coll(&f_cmpeq,
DEFAULT_COLLATION_OID,
value, track[j].value)))
{
match = true;
break;
}
if (j < firstcount1 && track[j].count == 1)
firstcount1 = j;
}
if (match)
{
/* Found a match */
track[j].count++;
/* This value may now need to "bubble up" in the track list */
while (j > 0 && track[j].count > track[j - 1].count)
{
swapDatum(track[j].value, track[j - 1].value);
swapInt(track[j].count, track[j - 1].count);
j--;
}
}
else
{
/* No match. Insert at head of count-1 list */
if (track_cnt < track_max)
track_cnt++;
for (j = track_cnt - 1; j > firstcount1; j--)
{
track[j].value = track[j - 1].value;
track[j].count = track[j - 1].count;
}
if (firstcount1 < track_cnt)
{
track[firstcount1].value = value;
track[firstcount1].count = 1;
}
}
}
/* We can only compute real stats if we found some non-null values. */
if (nonnull_cnt > 0)
{
int nmultiple,
summultiple;
stats->stats_valid = true;
/* Do the simple null-frac and width stats */
stats->stanullfrac = (double) null_cnt / (double) samplerows;
if (is_varwidth)
stats->stawidth = total_width / (double) nonnull_cnt;
else
stats->stawidth = stats->attrtype->typlen;
/* Count the number of values we found multiple times */
summultiple = 0;
for (nmultiple = 0; nmultiple < track_cnt; nmultiple++)
{
if (track[nmultiple].count == 1)
break;
summultiple += track[nmultiple].count;
}
if (nmultiple == 0)
{
/* If we found no repeated values, assume it's a unique column */
stats->stadistinct = -1.0;
}
else if (track_cnt < track_max && toowide_cnt == 0 &&
nmultiple == track_cnt)
{
/*
* Our track list includes every value in the sample, and every
* value appeared more than once. Assume the column has just
* these values.
*/
stats->stadistinct = track_cnt;
}
else
{
/*----------
* Estimate the number of distinct values using the estimator
* proposed by Haas and Stokes in IBM Research Report RJ 10025:
* n*d / (n - f1 + f1*n/N)
* where f1 is the number of distinct values that occurred
* exactly once in our sample of n rows (from a total of N),
* and d is the total number of distinct values in the sample.
* This is their Duj1 estimator; the other estimators they
* recommend are considerably more complex, and are numerically
* very unstable when n is much smaller than N.
*
* We assume (not very reliably!) that all the multiply-occurring
* values are reflected in the final track[] list, and the other
* nonnull values all appeared but once. (XXX this usually
* results in a drastic overestimate of ndistinct. Can we do
* any better?)
*----------
*/
int f1 = nonnull_cnt - summultiple;
int d = f1 + nmultiple;
double numer,
denom,
stadistinct;
numer = (double) samplerows *(double) d;
denom = (double) (samplerows - f1) +
(double) f1 *(double) samplerows / totalrows;
stadistinct = numer / denom;
/* Clamp to sane range in case of roundoff error */
if (stadistinct < (double) d)
stadistinct = (double) d;
if (stadistinct > totalrows)
stadistinct = totalrows;
stats->stadistinct = floor(stadistinct + 0.5);
}
/*
* If we estimated the number of distinct values at more than 10% of
* the total row count (a very arbitrary limit), then assume that
* stadistinct should scale with the row count rather than be a fixed
* value.
*/
if (stats->stadistinct > 0.1 * totalrows)
stats->stadistinct = -(stats->stadistinct / totalrows);
/*
* Decide how many values are worth storing as most-common values. If
* we are able to generate a complete MCV list (all the values in the
* sample will fit, and we think these are all the ones in the table),
* then do so. Otherwise, store only those values that are
* significantly more common than the (estimated) average. We set the
* threshold rather arbitrarily at 25% more than average, with at
* least 2 instances in the sample.
*/
if (track_cnt < track_max && toowide_cnt == 0 &&
stats->stadistinct > 0 &&
track_cnt <= num_mcv)
{
/* Track list includes all values seen, and all will fit */
num_mcv = track_cnt;
}
else
{
double ndistinct = stats->stadistinct;
double avgcount,
mincount;
if (ndistinct < 0)
ndistinct = -ndistinct * totalrows;
/* estimate # of occurrences in sample of a typical value */
avgcount = (double) samplerows / ndistinct;
/* set minimum threshold count to store a value */
mincount = avgcount * 1.25;
if (mincount < 2)
mincount = 2;
if (num_mcv > track_cnt)
num_mcv = track_cnt;
for (i = 0; i < num_mcv; i++)
{
if (track[i].count < mincount)
{
num_mcv = i;
break;
}
}
}
/* Generate MCV slot entry */
if (num_mcv > 0)
{
MemoryContext old_context;
Datum *mcv_values;
float4 *mcv_freqs;
/* Must copy the target values into anl_context */
old_context = MemoryContextSwitchTo(stats->anl_context);
mcv_values = (Datum *) palloc(num_mcv * sizeof(Datum));
mcv_freqs = (float4 *) palloc(num_mcv * sizeof(float4));
for (i = 0; i < num_mcv; i++)
{
mcv_values[i] = datumCopy(track[i].value,
stats->attrtype->typbyval,
stats->attrtype->typlen);
mcv_freqs[i] = (double) track[i].count / (double) samplerows;
}
MemoryContextSwitchTo(old_context);
stats->stakind[0] = STATISTIC_KIND_MCV;
stats->staop[0] = mystats->eqopr;
stats->stanumbers[0] = mcv_freqs;
stats->numnumbers[0] = num_mcv;
stats->stavalues[0] = mcv_values;
stats->numvalues[0] = num_mcv;
/*
* Accept the defaults for stats->statypid and others. They have
* been set before we were called (see vacuum.h)
*/
}
}
else if (null_cnt > 0)
{
/* We found only nulls; assume the column is entirely null */
stats->stats_valid = true;
stats->stanullfrac = 1.0;
if (is_varwidth)
stats->stawidth = 0; /* "unknown" */
else
stats->stawidth = stats->attrtype->typlen;
stats->stadistinct = 0.0; /* "unknown" */
}
/* We don't need to bother cleaning up any of our temporary palloc's */
}
| static void compute_scalar_stats | ( | VacAttrStatsP | stats, | |
| AnalyzeAttrFetchFunc | fetchfunc, | |||
| int | samplerows, | |||
| double | totalrows | |||
| ) | [static] |
Definition at line 2259 of file analyze.c.
References VacAttrStats::anl_context, Assert, VacAttrStats::attr, VacAttrStats::attrtype, compare_mcvs(), compare_scalars(), ScalarMCVItem::count, CurrentMemoryContext, datumCopy(), DatumGetCString, DatumGetPointer, StdAnalyzeData::eqopr, VacAttrStats::extra_data, ScalarMCVItem::first, i, StdAnalyzeData::ltopr, memmove, MemoryContextSwitchTo(), VacAttrStats::numnumbers, VacAttrStats::numvalues, palloc(), PG_DETOAST_DATUM, PointerGetDatum, PrepareSortSupportFromOrderingOp(), qsort, qsort_arg(), CompareScalarsContext::ssup, SortSupportData::ssup_collation, SortSupportData::ssup_cxt, SortSupportData::ssup_nulls_first, VacAttrStats::stadistinct, VacAttrStats::stakind, VacAttrStats::stanullfrac, VacAttrStats::stanumbers, VacAttrStats::staop, VacAttrStats::stats_valid, VacAttrStats::stavalues, VacAttrStats::stawidth, toast_raw_datum_size(), ScalarItem::tupno, CompareScalarsContext::tupnoLink, vacuum_delay_point(), ScalarItem::value, value, values, VARSIZE_ANY, and WIDTH_THRESHOLD.
{
int i;
int null_cnt = 0;
int nonnull_cnt = 0;
int toowide_cnt = 0;
double total_width = 0;
bool is_varlena = (!stats->attrtype->typbyval &&
stats->attrtype->typlen == -1);
bool is_varwidth = (!stats->attrtype->typbyval &&
stats->attrtype->typlen < 0);
double corr_xysum;
SortSupportData ssup;
ScalarItem *values;
int values_cnt = 0;
int *tupnoLink;
ScalarMCVItem *track;
int track_cnt = 0;
int num_mcv = stats->attr->attstattarget;
int num_bins = stats->attr->attstattarget;
StdAnalyzeData *mystats = (StdAnalyzeData *) stats->extra_data;
values = (ScalarItem *) palloc(samplerows * sizeof(ScalarItem));
tupnoLink = (int *) palloc(samplerows * sizeof(int));
track = (ScalarMCVItem *) palloc(num_mcv * sizeof(ScalarMCVItem));
memset(&ssup, 0, sizeof(ssup));
ssup.ssup_cxt = CurrentMemoryContext;
/* We always use the default collation for statistics */
ssup.ssup_collation = DEFAULT_COLLATION_OID;
ssup.ssup_nulls_first = false;
PrepareSortSupportFromOrderingOp(mystats->ltopr, &ssup);
/* Initial scan to find sortable values */
for (i = 0; i < samplerows; i++)
{
Datum value;
bool isnull;
vacuum_delay_point();
value = fetchfunc(stats, i, &isnull);
/* Check for null/nonnull */
if (isnull)
{
null_cnt++;
continue;
}
nonnull_cnt++;
/*
* If it's a variable-width field, add up widths for average width
* calculation. Note that if the value is toasted, we use the toasted
* width. We don't bother with this calculation if it's a fixed-width
* type.
*/
if (is_varlena)
{
total_width += VARSIZE_ANY(DatumGetPointer(value));
/*
* If the value is toasted, we want to detoast it just once to
* avoid repeated detoastings and resultant excess memory usage
* during the comparisons. Also, check to see if the value is
* excessively wide, and if so don't detoast at all --- just
* ignore the value.
*/
if (toast_raw_datum_size(value) > WIDTH_THRESHOLD)
{
toowide_cnt++;
continue;
}
value = PointerGetDatum(PG_DETOAST_DATUM(value));
}
else if (is_varwidth)
{
/* must be cstring */
total_width += strlen(DatumGetCString(value)) + 1;
}
/* Add it to the list to be sorted */
values[values_cnt].value = value;
values[values_cnt].tupno = values_cnt;
tupnoLink[values_cnt] = values_cnt;
values_cnt++;
}
/* We can only compute real stats if we found some sortable values. */
if (values_cnt > 0)
{
int ndistinct, /* # distinct values in sample */
nmultiple, /* # that appear multiple times */
num_hist,
dups_cnt;
int slot_idx = 0;
CompareScalarsContext cxt;
/* Sort the collected values */
cxt.ssup = &ssup;
cxt.tupnoLink = tupnoLink;
qsort_arg((void *) values, values_cnt, sizeof(ScalarItem),
compare_scalars, (void *) &cxt);
/*
* Now scan the values in order, find the most common ones, and also
* accumulate ordering-correlation statistics.
*
* To determine which are most common, we first have to count the
* number of duplicates of each value. The duplicates are adjacent in
* the sorted list, so a brute-force approach is to compare successive
* datum values until we find two that are not equal. However, that
* requires N-1 invocations of the datum comparison routine, which are
* completely redundant with work that was done during the sort. (The
* sort algorithm must at some point have compared each pair of items
* that are adjacent in the sorted order; otherwise it could not know
* that it's ordered the pair correctly.) We exploit this by having
* compare_scalars remember the highest tupno index that each
* ScalarItem has been found equal to. At the end of the sort, a
* ScalarItem's tupnoLink will still point to itself if and only if it
* is the last item of its group of duplicates (since the group will
* be ordered by tupno).
*/
corr_xysum = 0;
ndistinct = 0;
nmultiple = 0;
dups_cnt = 0;
for (i = 0; i < values_cnt; i++)
{
int tupno = values[i].tupno;
corr_xysum += ((double) i) * ((double) tupno);
dups_cnt++;
if (tupnoLink[tupno] == tupno)
{
/* Reached end of duplicates of this value */
ndistinct++;
if (dups_cnt > 1)
{
nmultiple++;
if (track_cnt < num_mcv ||
dups_cnt > track[track_cnt - 1].count)
{
/*
* Found a new item for the mcv list; find its
* position, bubbling down old items if needed. Loop
* invariant is that j points at an empty/ replaceable
* slot.
*/
int j;
if (track_cnt < num_mcv)
track_cnt++;
for (j = track_cnt - 1; j > 0; j--)
{
if (dups_cnt <= track[j - 1].count)
break;
track[j].count = track[j - 1].count;
track[j].first = track[j - 1].first;
}
track[j].count = dups_cnt;
track[j].first = i + 1 - dups_cnt;
}
}
dups_cnt = 0;
}
}
stats->stats_valid = true;
/* Do the simple null-frac and width stats */
stats->stanullfrac = (double) null_cnt / (double) samplerows;
if (is_varwidth)
stats->stawidth = total_width / (double) nonnull_cnt;
else
stats->stawidth = stats->attrtype->typlen;
if (nmultiple == 0)
{
/* If we found no repeated values, assume it's a unique column */
stats->stadistinct = -1.0;
}
else if (toowide_cnt == 0 && nmultiple == ndistinct)
{
/*
* Every value in the sample appeared more than once. Assume the
* column has just these values.
*/
stats->stadistinct = ndistinct;
}
else
{
/*----------
* Estimate the number of distinct values using the estimator
* proposed by Haas and Stokes in IBM Research Report RJ 10025:
* n*d / (n - f1 + f1*n/N)
* where f1 is the number of distinct values that occurred
* exactly once in our sample of n rows (from a total of N),
* and d is the total number of distinct values in the sample.
* This is their Duj1 estimator; the other estimators they
* recommend are considerably more complex, and are numerically
* very unstable when n is much smaller than N.
*
* Overwidth values are assumed to have been distinct.
*----------
*/
int f1 = ndistinct - nmultiple + toowide_cnt;
int d = f1 + nmultiple;
double numer,
denom,
stadistinct;
numer = (double) samplerows *(double) d;
denom = (double) (samplerows - f1) +
(double) f1 *(double) samplerows / totalrows;
stadistinct = numer / denom;
/* Clamp to sane range in case of roundoff error */
if (stadistinct < (double) d)
stadistinct = (double) d;
if (stadistinct > totalrows)
stadistinct = totalrows;
stats->stadistinct = floor(stadistinct + 0.5);
}
/*
* If we estimated the number of distinct values at more than 10% of
* the total row count (a very arbitrary limit), then assume that
* stadistinct should scale with the row count rather than be a fixed
* value.
*/
if (stats->stadistinct > 0.1 * totalrows)
stats->stadistinct = -(stats->stadistinct / totalrows);
/*
* Decide how many values are worth storing as most-common values. If
* we are able to generate a complete MCV list (all the values in the
* sample will fit, and we think these are all the ones in the table),
* then do so. Otherwise, store only those values that are
* significantly more common than the (estimated) average. We set the
* threshold rather arbitrarily at 25% more than average, with at
* least 2 instances in the sample. Also, we won't suppress values
* that have a frequency of at least 1/K where K is the intended
* number of histogram bins; such values might otherwise cause us to
* emit duplicate histogram bin boundaries. (We might end up with
* duplicate histogram entries anyway, if the distribution is skewed;
* but we prefer to treat such values as MCVs if at all possible.)
*/
if (track_cnt == ndistinct && toowide_cnt == 0 &&
stats->stadistinct > 0 &&
track_cnt <= num_mcv)
{
/* Track list includes all values seen, and all will fit */
num_mcv = track_cnt;
}
else
{
double ndistinct = stats->stadistinct;
double avgcount,
mincount,
maxmincount;
if (ndistinct < 0)
ndistinct = -ndistinct * totalrows;
/* estimate # of occurrences in sample of a typical value */
avgcount = (double) samplerows / ndistinct;
/* set minimum threshold count to store a value */
mincount = avgcount * 1.25;
if (mincount < 2)
mincount = 2;
/* don't let threshold exceed 1/K, however */
maxmincount = (double) samplerows / (double) num_bins;
if (mincount > maxmincount)
mincount = maxmincount;
if (num_mcv > track_cnt)
num_mcv = track_cnt;
for (i = 0; i < num_mcv; i++)
{
if (track[i].count < mincount)
{
num_mcv = i;
break;
}
}
}
/* Generate MCV slot entry */
if (num_mcv > 0)
{
MemoryContext old_context;
Datum *mcv_values;
float4 *mcv_freqs;
/* Must copy the target values into anl_context */
old_context = MemoryContextSwitchTo(stats->anl_context);
mcv_values = (Datum *) palloc(num_mcv * sizeof(Datum));
mcv_freqs = (float4 *) palloc(num_mcv * sizeof(float4));
for (i = 0; i < num_mcv; i++)
{
mcv_values[i] = datumCopy(values[track[i].first].value,
stats->attrtype->typbyval,
stats->attrtype->typlen);
mcv_freqs[i] = (double) track[i].count / (double) samplerows;
}
MemoryContextSwitchTo(old_context);
stats->stakind[slot_idx] = STATISTIC_KIND_MCV;
stats->staop[slot_idx] = mystats->eqopr;
stats->stanumbers[slot_idx] = mcv_freqs;
stats->numnumbers[slot_idx] = num_mcv;
stats->stavalues[slot_idx] = mcv_values;
stats->numvalues[slot_idx] = num_mcv;
/*
* Accept the defaults for stats->statypid and others. They have
* been set before we were called (see vacuum.h)
*/
slot_idx++;
}
/*
* Generate a histogram slot entry if there are at least two distinct
* values not accounted for in the MCV list. (This ensures the
* histogram won't collapse to empty or a singleton.)
*/
num_hist = ndistinct - num_mcv;
if (num_hist > num_bins)
num_hist = num_bins + 1;
if (num_hist >= 2)
{
MemoryContext old_context;
Datum *hist_values;
int nvals;
int pos,
posfrac,
delta,
deltafrac;
/* Sort the MCV items into position order to speed next loop */
qsort((void *) track, num_mcv,
sizeof(ScalarMCVItem), compare_mcvs);
/*
* Collapse out the MCV items from the values[] array.
*
* Note we destroy the values[] array here... but we don't need it
* for anything more. We do, however, still need values_cnt.
* nvals will be the number of remaining entries in values[].
*/
if (num_mcv > 0)
{
int src,
dest;
int j;
src = dest = 0;
j = 0; /* index of next interesting MCV item */
while (src < values_cnt)
{
int ncopy;
if (j < num_mcv)
{
int first = track[j].first;
if (src >= first)
{
/* advance past this MCV item */
src = first + track[j].count;
j++;
continue;
}
ncopy = first - src;
}
else
ncopy = values_cnt - src;
memmove(&values[dest], &values[src],
ncopy * sizeof(ScalarItem));
src += ncopy;
dest += ncopy;
}
nvals = dest;
}
else
nvals = values_cnt;
Assert(nvals >= num_hist);
/* Must copy the target values into anl_context */
old_context = MemoryContextSwitchTo(stats->anl_context);
hist_values = (Datum *) palloc(num_hist * sizeof(Datum));
/*
* The object of this loop is to copy the first and last values[]
* entries along with evenly-spaced values in between. So the
* i'th value is values[(i * (nvals - 1)) / (num_hist - 1)]. But
* computing that subscript directly risks integer overflow when
* the stats target is more than a couple thousand. Instead we
* add (nvals - 1) / (num_hist - 1) to pos at each step, tracking
* the integral and fractional parts of the sum separately.
*/
delta = (nvals - 1) / (num_hist - 1);
deltafrac = (nvals - 1) % (num_hist - 1);
pos = posfrac = 0;
for (i = 0; i < num_hist; i++)
{
hist_values[i] = datumCopy(values[pos].value,
stats->attrtype->typbyval,
stats->attrtype->typlen);
pos += delta;
posfrac += deltafrac;
if (posfrac >= (num_hist - 1))
{
/* fractional part exceeds 1, carry to integer part */
pos++;
posfrac -= (num_hist - 1);
}
}
MemoryContextSwitchTo(old_context);
stats->stakind[slot_idx] = STATISTIC_KIND_HISTOGRAM;
stats->staop[slot_idx] = mystats->ltopr;
stats->stavalues[slot_idx] = hist_values;
stats->numvalues[slot_idx] = num_hist;
/*
* Accept the defaults for stats->statypid and others. They have
* been set before we were called (see vacuum.h)
*/
slot_idx++;
}
/* Generate a correlation entry if there are multiple values */
if (values_cnt > 1)
{
MemoryContext old_context;
float4 *corrs;
double corr_xsum,
corr_x2sum;
/* Must copy the target values into anl_context */
old_context = MemoryContextSwitchTo(stats->anl_context);
corrs = (float4 *) palloc(sizeof(float4));
MemoryContextSwitchTo(old_context);
/*----------
* Since we know the x and y value sets are both
* 0, 1, ..., values_cnt-1
* we have sum(x) = sum(y) =
* (values_cnt-1)*values_cnt / 2
* and sum(x^2) = sum(y^2) =
* (values_cnt-1)*values_cnt*(2*values_cnt-1) / 6.
*----------
*/
corr_xsum = ((double) (values_cnt - 1)) *
((double) values_cnt) / 2.0;
corr_x2sum = ((double) (values_cnt - 1)) *
((double) values_cnt) * (double) (2 * values_cnt - 1) / 6.0;
/* And the correlation coefficient reduces to */
corrs[0] = (values_cnt * corr_xysum - corr_xsum * corr_xsum) /
(values_cnt * corr_x2sum - corr_xsum * corr_xsum);
stats->stakind[slot_idx] = STATISTIC_KIND_CORRELATION;
stats->staop[slot_idx] = mystats->ltopr;
stats->stanumbers[slot_idx] = corrs;
stats->numnumbers[slot_idx] = 1;
slot_idx++;
}
}
else if (nonnull_cnt == 0 && null_cnt > 0)
{
/* We found only nulls; assume the column is entirely null */
stats->stats_valid = true;
stats->stanullfrac = 1.0;
if (is_varwidth)
stats->stawidth = 0; /* "unknown" */
else
stats->stawidth = stats->attrtype->typlen;
stats->stadistinct = 0.0; /* "unknown" */
}
/* We don't need to bother cleaning up any of our temporary palloc's */
}
| static void do_analyze_rel | ( | Relation | onerel, | |
| VacuumStmt * | vacstmt, | |||
| AcquireSampleRowsFunc | acquirefunc, | |||
| BlockNumber | relpages, | |||
| bool | inh, | |||
| int | elevel | |||
| ) | [static] |
Definition at line 301 of file analyze.c.
References AccessShareLock, acquire_inherited_sample_rows(), ALLOCSET_DEFAULT_INITSIZE, ALLOCSET_DEFAULT_MAXSIZE, ALLOCSET_DEFAULT_MINSIZE, AllocSetContextCreate(), IndexVacuumInfo::analyze_only, AtEOXact_GUC(), attnameAttNum(), VacAttrStats::attr, AnlIndexData::attr_cnt, BuildIndexInfo(), compute_index_stats(), VacAttrStats::compute_stats, CurrentMemoryContext, elog, ereport, errcode(), errmsg(), ERROR, IndexVacuumInfo::estimated_count, examine_attribute(), get_attribute_options(), get_database_name(), get_namespace_name(), GetCurrentTimestamp(), GetUserIdAndSecContext(), i, IndexInfo::ii_Expressions, IndexInfo::ii_KeyAttrNumbers, IndexInfo::ii_NumIndexAttrs, IndexVacuumInfo::index, index_vacuum_cleanup(), AnlIndexData::indexInfo, InvalidAttrNumber, InvalidMultiXactId, InvalidTransactionId, IsAutoVacuumWorkerProcess(), lfirst, list_head(), list_length(), lnext, LOG, Log_autovacuum_min_duration, MemoryContextDelete(), MemoryContextResetAndDeleteChildren(), MemoryContextSwitchTo(), IndexVacuumInfo::message_level, VacAttrStats::minrows, MyDatabaseId, AttributeOpts::n_distinct, AttributeOpts::n_distinct_inherited, tupleDesc::natts, NewGUCNestLevel(), NIL, NoLock, NULL, IndexVacuumInfo::num_heap_tuples, VacuumStmt::options, palloc(), palloc0(), pfree(), pg_rusage_init(), pg_rusage_show(), pgstat_report_analyze(), RelationData::rd_att, RelationData::rd_rel, RelationGetNamespace, RelationGetNumberOfBlocks, RelationGetRelationName, RelationGetRelid, VacAttrStats::rows, SECURITY_RESTRICTED_OPERATION, SetUserIdAndSecContext(), VacAttrStats::stadistinct, std_fetch_func(), IndexVacuumInfo::strategy, strVal, TimestampDifferenceExceeds(), VacAttrStats::tupDesc, AnlIndexData::tupleFract, update_attstats(), VacuumStmt::va_cols, vac_close_indexes(), vac_open_indexes(), vac_update_relstats(), AnlIndexData::vacattrstats, VACOPT_VACUUM, and visibilitymap_count().
Referenced by analyze_rel().
{
int attr_cnt,
tcnt,
i,
ind;
Relation *Irel;
int nindexes;
bool hasindex;
VacAttrStats **vacattrstats;
AnlIndexData *indexdata;
int targrows,
numrows;
double totalrows,
totaldeadrows;
HeapTuple *rows;
PGRUsage ru0;
TimestampTz starttime = 0;
MemoryContext caller_context;
Oid save_userid;
int save_sec_context;
int save_nestlevel;
if (inh)
ereport(elevel,
(errmsg("analyzing \"%s.%s\" inheritance tree",
get_namespace_name(RelationGetNamespace(onerel)),
RelationGetRelationName(onerel))));
else
ereport(elevel,
(errmsg("analyzing \"%s.%s\"",
get_namespace_name(RelationGetNamespace(onerel)),
RelationGetRelationName(onerel))));
/*
* Set up a working context so that we can easily free whatever junk gets
* created.
*/
anl_context = AllocSetContextCreate(CurrentMemoryContext,
"Analyze",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
caller_context = MemoryContextSwitchTo(anl_context);
/*
* Switch to the table owner's userid, so that any index functions are run
* as that user. Also lock down security-restricted operations and
* arrange to make GUC variable changes local to this command.
*/
GetUserIdAndSecContext(&save_userid, &save_sec_context);
SetUserIdAndSecContext(onerel->rd_rel->relowner,
save_sec_context | SECURITY_RESTRICTED_OPERATION);
save_nestlevel = NewGUCNestLevel();
/* measure elapsed time iff autovacuum logging requires it */
if (IsAutoVacuumWorkerProcess() && Log_autovacuum_min_duration >= 0)
{
pg_rusage_init(&ru0);
if (Log_autovacuum_min_duration > 0)
starttime = GetCurrentTimestamp();
}
/*
* Determine which columns to analyze
*
* Note that system attributes are never analyzed.
*/
if (vacstmt->va_cols != NIL)
{
ListCell *le;
vacattrstats = (VacAttrStats **) palloc(list_length(vacstmt->va_cols) *
sizeof(VacAttrStats *));
tcnt = 0;
foreach(le, vacstmt->va_cols)
{
char *col = strVal(lfirst(le));
i = attnameAttNum(onerel, col, false);
if (i == InvalidAttrNumber)
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_COLUMN),
errmsg("column \"%s\" of relation \"%s\" does not exist",
col, RelationGetRelationName(onerel))));
vacattrstats[tcnt] = examine_attribute(onerel, i, NULL);
if (vacattrstats[tcnt] != NULL)
tcnt++;
}
attr_cnt = tcnt;
}
else
{
attr_cnt = onerel->rd_att->natts;
vacattrstats = (VacAttrStats **)
palloc(attr_cnt * sizeof(VacAttrStats *));
tcnt = 0;
for (i = 1; i <= attr_cnt; i++)
{
vacattrstats[tcnt] = examine_attribute(onerel, i, NULL);
if (vacattrstats[tcnt] != NULL)
tcnt++;
}
attr_cnt = tcnt;
}
/*
* Open all indexes of the relation, and see if there are any analyzable
* columns in the indexes. We do not analyze index columns if there was
* an explicit column list in the ANALYZE command, however. If we are
* doing a recursive scan, we don't want to touch the parent's indexes at
* all.
*/
if (!inh)
vac_open_indexes(onerel, AccessShareLock, &nindexes, &Irel);
else
{
Irel = NULL;
nindexes = 0;
}
hasindex = (nindexes > 0);
indexdata = NULL;
if (hasindex)
{
indexdata = (AnlIndexData *) palloc0(nindexes * sizeof(AnlIndexData));
for (ind = 0; ind < nindexes; ind++)
{
AnlIndexData *thisdata = &indexdata[ind];
IndexInfo *indexInfo;
thisdata->indexInfo = indexInfo = BuildIndexInfo(Irel[ind]);
thisdata->tupleFract = 1.0; /* fix later if partial */
if (indexInfo->ii_Expressions != NIL && vacstmt->va_cols == NIL)
{
ListCell *indexpr_item = list_head(indexInfo->ii_Expressions);
thisdata->vacattrstats = (VacAttrStats **)
palloc(indexInfo->ii_NumIndexAttrs * sizeof(VacAttrStats *));
tcnt = 0;
for (i = 0; i < indexInfo->ii_NumIndexAttrs; i++)
{
int keycol = indexInfo->ii_KeyAttrNumbers[i];
if (keycol == 0)
{
/* Found an index expression */
Node *indexkey;
if (indexpr_item == NULL) /* shouldn't happen */
elog(ERROR, "too few entries in indexprs list");
indexkey = (Node *) lfirst(indexpr_item);
indexpr_item = lnext(indexpr_item);
thisdata->vacattrstats[tcnt] =
examine_attribute(Irel[ind], i + 1, indexkey);
if (thisdata->vacattrstats[tcnt] != NULL)
tcnt++;
}
}
thisdata->attr_cnt = tcnt;
}
}
}
/*
* Determine how many rows we need to sample, using the worst case from
* all analyzable columns. We use a lower bound of 100 rows to avoid
* possible overflow in Vitter's algorithm. (Note: that will also be the
* target in the corner case where there are no analyzable columns.)
*/
targrows = 100;
for (i = 0; i < attr_cnt; i++)
{
if (targrows < vacattrstats[i]->minrows)
targrows = vacattrstats[i]->minrows;
}
for (ind = 0; ind < nindexes; ind++)
{
AnlIndexData *thisdata = &indexdata[ind];
for (i = 0; i < thisdata->attr_cnt; i++)
{
if (targrows < thisdata->vacattrstats[i]->minrows)
targrows = thisdata->vacattrstats[i]->minrows;
}
}
/*
* Acquire the sample rows
*/
rows = (HeapTuple *) palloc(targrows * sizeof(HeapTuple));
if (inh)
numrows = acquire_inherited_sample_rows(onerel, elevel,
rows, targrows,
&totalrows, &totaldeadrows);
else
numrows = (*acquirefunc) (onerel, elevel,
rows, targrows,
&totalrows, &totaldeadrows);
/*
* Compute the statistics. Temporary results during the calculations for
* each column are stored in a child context. The calc routines are
* responsible to make sure that whatever they store into the VacAttrStats
* structure is allocated in anl_context.
*/
if (numrows > 0)
{
MemoryContext col_context,
old_context;
col_context = AllocSetContextCreate(anl_context,
"Analyze Column",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
old_context = MemoryContextSwitchTo(col_context);
for (i = 0; i < attr_cnt; i++)
{
VacAttrStats *stats = vacattrstats[i];
AttributeOpts *aopt;
stats->rows = rows;
stats->tupDesc = onerel->rd_att;
(*stats->compute_stats) (stats,
std_fetch_func,
numrows,
totalrows);
/*
* If the appropriate flavor of the n_distinct option is
* specified, override with the corresponding value.
*/
aopt = get_attribute_options(onerel->rd_id, stats->attr->attnum);
if (aopt != NULL)
{
float8 n_distinct;
n_distinct = inh ? aopt->n_distinct_inherited : aopt->n_distinct;
if (n_distinct != 0.0)
stats->stadistinct = n_distinct;
}
MemoryContextResetAndDeleteChildren(col_context);
}
if (hasindex)
compute_index_stats(onerel, totalrows,
indexdata, nindexes,
rows, numrows,
col_context);
MemoryContextSwitchTo(old_context);
MemoryContextDelete(col_context);
/*
* Emit the completed stats rows into pg_statistic, replacing any
* previous statistics for the target columns. (If there are stats in
* pg_statistic for columns we didn't process, we leave them alone.)
*/
update_attstats(RelationGetRelid(onerel), inh,
attr_cnt, vacattrstats);
for (ind = 0; ind < nindexes; ind++)
{
AnlIndexData *thisdata = &indexdata[ind];
update_attstats(RelationGetRelid(Irel[ind]), false,
thisdata->attr_cnt, thisdata->vacattrstats);
}
}
/*
* Update pages/tuples stats in pg_class ... but not if we're doing
* inherited stats.
*/
if (!inh)
vac_update_relstats(onerel,
relpages,
totalrows,
visibilitymap_count(onerel),
hasindex,
InvalidTransactionId,
InvalidMultiXactId);
/*
* Same for indexes. Vacuum always scans all indexes, so if we're part of
* VACUUM ANALYZE, don't overwrite the accurate count already inserted by
* VACUUM.
*/
if (!inh && !(vacstmt->options & VACOPT_VACUUM))
{
for (ind = 0; ind < nindexes; ind++)
{
AnlIndexData *thisdata = &indexdata[ind];
double totalindexrows;
totalindexrows = ceil(thisdata->tupleFract * totalrows);
vac_update_relstats(Irel[ind],
RelationGetNumberOfBlocks(Irel[ind]),
totalindexrows,
0,
false,
InvalidTransactionId,
InvalidMultiXactId);
}
}
/*
* Report ANALYZE to the stats collector, too. However, if doing
* inherited stats we shouldn't report, because the stats collector only
* tracks per-table stats.
*/
if (!inh)
pgstat_report_analyze(onerel, totalrows, totaldeadrows);
/* If this isn't part of VACUUM ANALYZE, let index AMs do cleanup */
if (!(vacstmt->options & VACOPT_VACUUM))
{
for (ind = 0; ind < nindexes; ind++)
{
IndexBulkDeleteResult *stats;
IndexVacuumInfo ivinfo;
ivinfo.index = Irel[ind];
ivinfo.analyze_only = true;
ivinfo.estimated_count = true;
ivinfo.message_level = elevel;
ivinfo.num_heap_tuples = onerel->rd_rel->reltuples;
ivinfo.strategy = vac_strategy;
stats = index_vacuum_cleanup(&ivinfo, NULL);
if (stats)
pfree(stats);
}
}
/* Done with indexes */
vac_close_indexes(nindexes, Irel, NoLock);
/* Log the action if appropriate */
if (IsAutoVacuumWorkerProcess() && Log_autovacuum_min_duration >= 0)
{
if (Log_autovacuum_min_duration == 0 ||
TimestampDifferenceExceeds(starttime, GetCurrentTimestamp(),
Log_autovacuum_min_duration))
ereport(LOG,
(errmsg("automatic analyze of table \"%s.%s.%s\" system usage: %s",
get_database_name(MyDatabaseId),
get_namespace_name(RelationGetNamespace(onerel)),
RelationGetRelationName(onerel),
pg_rusage_show(&ru0))));
}
/* Roll back any GUC changes executed by index functions */
AtEOXact_GUC(false, save_nestlevel);
/* Restore userid and security context */
SetUserIdAndSecContext(save_userid, save_sec_context);
/* Restore current context and release memory */
MemoryContextSwitchTo(caller_context);
MemoryContextDelete(anl_context);
anl_context = NULL;
}
| static VacAttrStats * examine_attribute | ( | Relation | onerel, | |
| int | attnum, | |||
| Node * | index_expr | |||
| ) | [static] |
Definition at line 857 of file analyze.c.
References VacAttrStats::anl_context, VacAttrStats::attr, ATTRIBUTE_FIXED_PART_SIZE, tupleDesc::attrs, VacAttrStats::attrtype, VacAttrStats::attrtypid, VacAttrStats::attrtypmod, VacAttrStats::compute_stats, DatumGetBool, elog, ERROR, exprType(), exprTypmod(), GETSTRUCT, heap_freetuple(), HeapTupleIsValid, i, VacAttrStats::minrows, NULL, ObjectIdGetDatum, OidFunctionCall1, OidIsValid, palloc(), palloc0(), pfree(), PointerGetDatum, RelationData::rd_att, SearchSysCacheCopy1, VacAttrStats::statypalign, VacAttrStats::statypbyval, VacAttrStats::statypid, VacAttrStats::statyplen, std_typanalyze(), VacAttrStats::tupattnum, and TYPEOID.
Referenced by do_analyze_rel().
{
Form_pg_attribute attr = onerel->rd_att->attrs[attnum - 1];
HeapTuple typtuple;
VacAttrStats *stats;
int i;
bool ok;
/* Never analyze dropped columns */
if (attr->attisdropped)
return NULL;
/* Don't analyze column if user has specified not to */
if (attr->attstattarget == 0)
return NULL;
/*
* Create the VacAttrStats struct. Note that we only have a copy of the
* fixed fields of the pg_attribute tuple.
*/
stats = (VacAttrStats *) palloc0(sizeof(VacAttrStats));
stats->attr = (Form_pg_attribute) palloc(ATTRIBUTE_FIXED_PART_SIZE);
memcpy(stats->attr, attr, ATTRIBUTE_FIXED_PART_SIZE);
/*
* When analyzing an expression index, believe the expression tree's type
* not the column datatype --- the latter might be the opckeytype storage
* type of the opclass, which is not interesting for our purposes. (Note:
* if we did anything with non-expression index columns, we'd need to
* figure out where to get the correct type info from, but for now that's
* not a problem.) It's not clear whether anyone will care about the
* typmod, but we store that too just in case.
*/
if (index_expr)
{
stats->attrtypid = exprType(index_expr);
stats->attrtypmod = exprTypmod(index_expr);
}
else
{
stats->attrtypid = attr->atttypid;
stats->attrtypmod = attr->atttypmod;
}
typtuple = SearchSysCacheCopy1(TYPEOID,
ObjectIdGetDatum(stats->attrtypid));
if (!HeapTupleIsValid(typtuple))
elog(ERROR, "cache lookup failed for type %u", stats->attrtypid);
stats->attrtype = (Form_pg_type) GETSTRUCT(typtuple);
stats->anl_context = anl_context;
stats->tupattnum = attnum;
/*
* The fields describing the stats->stavalues[n] element types default to
* the type of the data being analyzed, but the type-specific typanalyze
* function can change them if it wants to store something else.
*/
for (i = 0; i < STATISTIC_NUM_SLOTS; i++)
{
stats->statypid[i] = stats->attrtypid;
stats->statyplen[i] = stats->attrtype->typlen;
stats->statypbyval[i] = stats->attrtype->typbyval;
stats->statypalign[i] = stats->attrtype->typalign;
}
/*
* Call the type-specific typanalyze function. If none is specified, use
* std_typanalyze().
*/
if (OidIsValid(stats->attrtype->typanalyze))
ok = DatumGetBool(OidFunctionCall1(stats->attrtype->typanalyze,
PointerGetDatum(stats)));
else
ok = std_typanalyze(stats);
if (!ok || stats->compute_stats == NULL || stats->minrows <= 0)
{
heap_freetuple(typtuple);
pfree(stats->attr);
pfree(stats);
return NULL;
}
return stats;
}
| static Datum ind_fetch_func | ( | VacAttrStatsP | stats, | |
| int | rownum, | |||
| bool * | isNull | |||
| ) | [static] |
Definition at line 1768 of file analyze.c.
References VacAttrStats::exprnulls, VacAttrStats::exprvals, i, and VacAttrStats::rowstride.
Referenced by compute_index_stats().
| static Datum std_fetch_func | ( | VacAttrStatsP | stats, | |
| int | rownum, | |||
| bool * | isNull | |||
| ) | [static] |
Definition at line 1752 of file analyze.c.
References heap_getattr, VacAttrStats::rows, VacAttrStats::tupattnum, and VacAttrStats::tupDesc.
Referenced by do_analyze_rel().
| bool std_typanalyze | ( | VacAttrStats * | stats | ) |
Definition at line 1848 of file analyze.c.
References VacAttrStats::attr, VacAttrStats::attrtypid, VacAttrStats::compute_stats, default_statistics_target, StdAnalyzeData::eqfunc, StdAnalyzeData::eqopr, VacAttrStats::extra_data, get_opcode(), get_sort_group_operators(), StdAnalyzeData::ltopr, VacAttrStats::minrows, NULL, OidIsValid, and palloc().
Referenced by array_typanalyze(), and examine_attribute().
{
Form_pg_attribute attr = stats->attr;
Oid ltopr;
Oid eqopr;
StdAnalyzeData *mystats;
/* If the attstattarget column is negative, use the default value */
/* NB: it is okay to scribble on stats->attr since it's a copy */
if (attr->attstattarget < 0)
attr->attstattarget = default_statistics_target;
/* Look for default "<" and "=" operators for column's type */
get_sort_group_operators(stats->attrtypid,
false, false, false,
<opr, &eqopr, NULL,
NULL);
/* If column has no "=" operator, we can't do much of anything */
if (!OidIsValid(eqopr))
return false;
/* Save the operator info for compute_stats routines */
mystats = (StdAnalyzeData *) palloc(sizeof(StdAnalyzeData));
mystats->eqopr = eqopr;
mystats->eqfunc = get_opcode(eqopr);
mystats->ltopr = ltopr;
stats->extra_data = mystats;
/*
* Determine which standard statistics algorithm to use
*/
if (OidIsValid(ltopr))
{
/* Seems to be a scalar datatype */
stats->compute_stats = compute_scalar_stats;
/*--------------------
* The following choice of minrows is based on the paper
* "Random sampling for histogram construction: how much is enough?"
* by Surajit Chaudhuri, Rajeev Motwani and Vivek Narasayya, in
* Proceedings of ACM SIGMOD International Conference on Management
* of Data, 1998, Pages 436-447. Their Corollary 1 to Theorem 5
* says that for table size n, histogram size k, maximum relative
* error in bin size f, and error probability gamma, the minimum
* random sample size is
* r = 4 * k * ln(2*n/gamma) / f^2
* Taking f = 0.5, gamma = 0.01, n = 10^6 rows, we obtain
* r = 305.82 * k
* Note that because of the log function, the dependence on n is
* quite weak; even at n = 10^12, a 300*k sample gives <= 0.66
* bin size error with probability 0.99. So there's no real need to
* scale for n, which is a good thing because we don't necessarily
* know it at this point.
*--------------------
*/
stats->minrows = 300 * attr->attstattarget;
}
else
{
/* Can't do much but the minimal stuff */
stats->compute_stats = compute_minimal_stats;
/* Might as well use the same minrows as above */
stats->minrows = 300 * attr->attstattarget;
}
return true;
}
| static void update_attstats | ( | Oid | relid, | |
| bool | inh, | |||
| int | natts, | |||
| VacAttrStats ** | vacattrstats | |||
| ) | [static] |
Definition at line 1615 of file analyze.c.
References Anum_pg_statistic_staattnum, Anum_pg_statistic_stadistinct, Anum_pg_statistic_stainherit, Anum_pg_statistic_stakind1, Anum_pg_statistic_stanullfrac, Anum_pg_statistic_stanumbers1, Anum_pg_statistic_staop1, Anum_pg_statistic_starelid, Anum_pg_statistic_stavalues1, Anum_pg_statistic_stawidth, VacAttrStats::attr, BoolGetDatum, CatalogUpdateIndexes(), construct_array(), Float4GetDatum(), FLOAT4OID, heap_close, heap_form_tuple(), heap_freetuple(), heap_modify_tuple(), heap_open(), HeapTupleIsValid, i, Int16GetDatum, Int32GetDatum, VacAttrStats::numnumbers, VacAttrStats::numvalues, ObjectIdGetDatum, palloc(), PointerGetDatum, RelationGetDescr, ReleaseSysCache(), RowExclusiveLock, SearchSysCache3, simple_heap_insert(), simple_heap_update(), VacAttrStats::stadistinct, VacAttrStats::stakind, VacAttrStats::stanullfrac, VacAttrStats::stanumbers, VacAttrStats::staop, StatisticRelationId, STATRELATTINH, VacAttrStats::stats_valid, VacAttrStats::statypalign, VacAttrStats::statypbyval, VacAttrStats::statypid, VacAttrStats::statyplen, VacAttrStats::stavalues, VacAttrStats::stawidth, HeapTupleData::t_self, and values.
Referenced by do_analyze_rel().
{
Relation sd;
int attno;
if (natts <= 0)
return; /* nothing to do */
sd = heap_open(StatisticRelationId, RowExclusiveLock);
for (attno = 0; attno < natts; attno++)
{
VacAttrStats *stats = vacattrstats[attno];
HeapTuple stup,
oldtup;
int i,
k,
n;
Datum values[Natts_pg_statistic];
bool nulls[Natts_pg_statistic];
bool replaces[Natts_pg_statistic];
/* Ignore attr if we weren't able to collect stats */
if (!stats->stats_valid)
continue;
/*
* Construct a new pg_statistic tuple
*/
for (i = 0; i < Natts_pg_statistic; ++i)
{
nulls[i] = false;
replaces[i] = true;
}
values[Anum_pg_statistic_starelid - 1] = ObjectIdGetDatum(relid);
values[Anum_pg_statistic_staattnum - 1] = Int16GetDatum(stats->attr->attnum);
values[Anum_pg_statistic_stainherit - 1] = BoolGetDatum(inh);
values[Anum_pg_statistic_stanullfrac - 1] = Float4GetDatum(stats->stanullfrac);
values[Anum_pg_statistic_stawidth - 1] = Int32GetDatum(stats->stawidth);
values[Anum_pg_statistic_stadistinct - 1] = Float4GetDatum(stats->stadistinct);
i = Anum_pg_statistic_stakind1 - 1;
for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
{
values[i++] = Int16GetDatum(stats->stakind[k]); /* stakindN */
}
i = Anum_pg_statistic_staop1 - 1;
for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
{
values[i++] = ObjectIdGetDatum(stats->staop[k]); /* staopN */
}
i = Anum_pg_statistic_stanumbers1 - 1;
for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
{
int nnum = stats->numnumbers[k];
if (nnum > 0)
{
Datum *numdatums = (Datum *) palloc(nnum * sizeof(Datum));
ArrayType *arry;
for (n = 0; n < nnum; n++)
numdatums[n] = Float4GetDatum(stats->stanumbers[k][n]);
/* XXX knows more than it should about type float4: */
arry = construct_array(numdatums, nnum,
FLOAT4OID,
sizeof(float4), FLOAT4PASSBYVAL, 'i');
values[i++] = PointerGetDatum(arry); /* stanumbersN */
}
else
{
nulls[i] = true;
values[i++] = (Datum) 0;
}
}
i = Anum_pg_statistic_stavalues1 - 1;
for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
{
if (stats->numvalues[k] > 0)
{
ArrayType *arry;
arry = construct_array(stats->stavalues[k],
stats->numvalues[k],
stats->statypid[k],
stats->statyplen[k],
stats->statypbyval[k],
stats->statypalign[k]);
values[i++] = PointerGetDatum(arry); /* stavaluesN */
}
else
{
nulls[i] = true;
values[i++] = (Datum) 0;
}
}
/* Is there already a pg_statistic tuple for this attribute? */
oldtup = SearchSysCache3(STATRELATTINH,
ObjectIdGetDatum(relid),
Int16GetDatum(stats->attr->attnum),
BoolGetDatum(inh));
if (HeapTupleIsValid(oldtup))
{
/* Yes, replace it */
stup = heap_modify_tuple(oldtup,
RelationGetDescr(sd),
values,
nulls,
replaces);
ReleaseSysCache(oldtup);
simple_heap_update(sd, &stup->t_self, stup);
}
else
{
/* No, insert new tuple */
stup = heap_form_tuple(RelationGetDescr(sd), values, nulls);
simple_heap_insert(sd, stup);
}
/* update indexes too */
CatalogUpdateIndexes(sd, stup);
heap_freetuple(stup);
}
heap_close(sd, RowExclusiveLock);
}
MemoryContext anl_context = NULL [static] |
| int default_statistics_target = 100 |
Definition at line 80 of file analyze.c.
Referenced by range_typanalyze(), std_typanalyze(), and ts_typanalyze().
BufferAccessStrategy vac_strategy [static] |
1.7.1