/*
* pgstat_index -- returns live/dead tuples info in a generic index
*/
static Datum
pgstat_index(Relation rel, BlockNumber start, pgstat_page pagefn,
FunctionCallInfo fcinfo)
{
BlockNumber nblocks;
BlockNumber blkno;
BufferAccessStrategy bstrategy;
pgstattuple_type stat = {0};
/* prepare access strategy for this index */
bstrategy = GetAccessStrategy(BAS_BULKREAD);
blkno = start;
for (;;)
{
/* Get the current relation length */
LockRelationForExtension(rel, ExclusiveLock);
nblocks = RelationGetNumberOfBlocks(rel);
UnlockRelationForExtension(rel, ExclusiveLock);
/* Quit if we've scanned the whole relation */
if (blkno >= nblocks)
{
stat.table_len = (uint64) nblocks *BLCKSZ;
break;
}
for (; blkno < nblocks; blkno++)
{
CHECK_FOR_INTERRUPTS();
pagefn(&stat, rel, blkno, bstrategy);
}
}
relation_close(rel, AccessShareLock);
return build_pgstattuple_type(&stat, fcinfo);
}
/*
* Build a new bloom index.
*/
IndexBuildResult *
blbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
BloomBuildState buildstate;
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* Initialize the meta page */
BloomInitMetapage(index);
/* Initialize the bloom build state */
memset(&buildstate, 0, sizeof(buildstate));
initBloomState(&buildstate.blstate, index);
buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Bloom build temporary context",
ALLOCSET_DEFAULT_SIZES);
initCachedPage(&buildstate);
/* Do the heap scan */
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
bloomBuildCallback, (void *) &buildstate);
/*
* There are could be some items in cached page. Flush this page if
* needed.
*/
if (buildstate.count > 0)
flushCachedPage(index, &buildstate);
MemoryContextDelete(buildstate.tmpCtx);
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = result->index_tuples = reltuples;
return result;
}
Datum
pg_relpagesbyid(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 relpages;
Relation rel;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pgstattuple functions"))));
rel = relation_open(relid, AccessShareLock);
/* note: this will work OK on non-local temp tables */
relpages = RelationGetNumberOfBlocks(rel);
relation_close(rel, AccessShareLock);
PG_RETURN_INT64(relpages);
}
/* No need for superuser checks in v1.5, see above */
Datum
pg_relpages_v1_5(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_PP(0);
int64 relpages;
Relation rel;
RangeVar *relrv;
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
/* only some relkinds have storage */
check_relation_relkind(rel);
/* note: this will work OK on non-local temp tables */
relpages = RelationGetNumberOfBlocks(rel);
relation_close(rel, AccessShareLock);
PG_RETURN_INT64(relpages);
}
/*
* hashbuild() -- build a new hash index.
*/
Datum
hashbuild(PG_FUNCTION_ARGS)
{
Relation heap = (Relation) PG_GETARG_POINTER(0);
Relation index = (Relation) PG_GETARG_POINTER(1);
IndexInfo *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
IndexBuildResult *result;
double reltuples;
HashBuildState buildstate;
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* initialize the hash index metadata page */
_hash_metapinit(index);
/* build the index */
buildstate.indtuples = 0;
/* do the heap scan */
reltuples = IndexBuildHeapScan(heap, index, indexInfo,
hashbuildCallback, (void *) &buildstate);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
PG_RETURN_POINTER(result);
}
/* --------------------------------------------------------
* pg_relpages()
*
* Get a number of pages of the table/index.
*
* Usage: SELECT pg_relpages('t1');
* SELECT pg_relpages('t1_pkey');
* --------------------------------------------------------
*/
Datum
pg_relpages(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_P(0);
Relation rel;
RangeVar *relrv;
int4 relpages;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pgstattuple functions"))));
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
relpages = RelationGetNumberOfBlocks(rel);
relation_close(rel, AccessShareLock);
PG_RETURN_INT32(relpages);
}
/*
* GetPageWithFreeSpace - try to find a page in the given relation with
* at least the specified amount of free space.
*
* If successful, return the block number; if not, return InvalidBlockNumber.
*
* The caller must be prepared for the possibility that the returned page
* will turn out to have too little space available by the time the caller
* gets a lock on it. In that case, the caller should report the actual
* amount of free space available on that page and then try again (see
* RecordAndGetPageWithFreeSpace). If InvalidBlockNumber is returned,
* extend the relation.
*
* For very small heap relations that don't have a FSM, we try every other
* page before extending the relation. To keep track of which pages have
* been tried, initialize a local in-memory map of pages.
*/
BlockNumber
GetPageWithFreeSpace(Relation rel, Size spaceNeeded, bool check_fsm_only)
{
uint8 min_cat = fsm_space_needed_to_cat(spaceNeeded);
BlockNumber target_block,
nblocks;
/* First try the FSM, if it exists. */
target_block = fsm_search(rel, min_cat);
if (target_block == InvalidBlockNumber &&
(rel->rd_rel->relkind == RELKIND_RELATION ||
rel->rd_rel->relkind == RELKIND_TOASTVALUE) &&
!check_fsm_only)
{
nblocks = RelationGetNumberOfBlocks(rel);
if (nblocks > HEAP_FSM_CREATION_THRESHOLD)
{
/*
* If the FSM knows nothing of the rel, try the last page before
* we give up and extend. This avoids one-tuple-per-page syndrome
* during bootstrapping or in a recently-started system.
*/
target_block = nblocks - 1;
}
else if (nblocks > 0)
{
/* Create or update local map and get first candidate block. */
fsm_local_set(rel, nblocks);
target_block = fsm_local_search();
}
}
return target_block;
}
/*
* Post-VACUUM cleanup.
*
* Result: a palloc'd struct containing statistical info for VACUUM displays.
*/
Datum bingo_vacuumcleanup(PG_FUNCTION_ARGS) {
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
Relation rel = info->index;
BlockNumber num_pages = 0;
elog(NOTICE, "start test vacuum");
/*
* If bulkdelete wasn't called, return NULL signifying no change
* Note: this covers the analyze_only case too
*/
if (stats == NULL) {
PG_RETURN_POINTER(NULL);
}
/*
* update statistics
*/
num_pages = RelationGetNumberOfBlocks(rel);
stats->num_pages = num_pages;
stats->num_index_tuples = 1;
stats->estimated_count = false;
PG_RETURN_POINTER(stats);
}
/*
* Main entry point to GiST index build. Initially calls insert over and over,
* but switches to more efficient buffering build algorithm after a certain
* number of tuples (unless buffering mode is disabled).
*/
Datum
gistbuild(PG_FUNCTION_ARGS)
{
Relation heap = (Relation) PG_GETARG_POINTER(0);
Relation index = (Relation) PG_GETARG_POINTER(1);
IndexInfo *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
IndexBuildResult *result;
double reltuples;
GISTBuildState buildstate;
Buffer buffer;
Page page;
MemoryContext oldcxt = CurrentMemoryContext;
int fillfactor;
buildstate.indexrel = index;
if (index->rd_options)
{
/* Get buffering mode from the options string */
GiSTOptions *options = (GiSTOptions *) index->rd_options;
char *bufferingMode = (char *) options + options->bufferingModeOffset;
if (strcmp(bufferingMode, "on") == 0)
buildstate.bufferingMode = GIST_BUFFERING_STATS;
else if (strcmp(bufferingMode, "off") == 0)
buildstate.bufferingMode = GIST_BUFFERING_DISABLED;
else
buildstate.bufferingMode = GIST_BUFFERING_AUTO;
fillfactor = options->fillfactor;
}
else
{
/*
* By default, switch to buffering mode when the index grows too large
* to fit in cache.
*/
buildstate.bufferingMode = GIST_BUFFERING_AUTO;
fillfactor = GIST_DEFAULT_FILLFACTOR;
}
/* Calculate target amount of free space to leave on pages */
buildstate.freespace = BLCKSZ * (100 - fillfactor) / 100;
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* no locking is needed */
buildstate.giststate = initGISTstate(index);
/*
* Create a temporary memory context that is reset once for each tuple
* processed. (Note: we don't bother to make this a child of the
* giststate's scanCxt, so we have to delete it separately at the end.)
*/
buildstate.giststate->tempCxt = createTempGistContext();
/* initialize the root page */
buffer = gistNewBuffer(index);
Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
page = BufferGetPage(buffer);
START_CRIT_SECTION();
GISTInitBuffer(buffer, F_LEAF);
MarkBufferDirty(buffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
XLogRecData rdata;
rdata.data = (char *) &(index->rd_node);
rdata.len = sizeof(RelFileNode);
rdata.buffer = InvalidBuffer;
rdata.next = NULL;
recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX, &rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
else
PageSetLSN(page, gistGetFakeLSN(heap));
UnlockReleaseBuffer(buffer);
END_CRIT_SECTION();
/* build the index */
buildstate.indtuples = 0;
buildstate.indtuplesSize = 0;
/*
* Do the heap scan.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
gistBuildCallback, (void *) &buildstate);
/*
* If buffering was used, flush out all the tuples that are still in the
* buffers.
*/
if (buildstate.bufferingMode == GIST_BUFFERING_ACTIVE)
{
elog(DEBUG1, "all tuples processed, emptying buffers");
gistEmptyAllBuffers(&buildstate);
gistFreeBuildBuffers(buildstate.gfbb);
}
/* okay, all heap tuples are indexed */
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(buildstate.giststate->tempCxt);
freeGISTstate(buildstate.giststate);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = (double) buildstate.indtuples;
PG_RETURN_POINTER(result);
}
/*
* hashbuild() -- build a new hash index.
*/
IndexBuildResult *
hashbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
BlockNumber relpages;
double reltuples;
double allvisfrac;
uint32 num_buckets;
long sort_threshold;
HashBuildState buildstate;
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* Estimate the number of rows currently present in the table */
estimate_rel_size(heap, NULL, &relpages, &reltuples, &allvisfrac);
/* Initialize the hash index metadata page and initial buckets */
num_buckets = _hash_init(index, reltuples, MAIN_FORKNUM);
/*
* If we just insert the tuples into the index in scan order, then
* (assuming their hash codes are pretty random) there will be no locality
* of access to the index, and if the index is bigger than available RAM
* then we'll thrash horribly. To prevent that scenario, we can sort the
* tuples by (expected) bucket number. However, such a sort is useless
* overhead when the index does fit in RAM. We choose to sort if the
* initial index size exceeds maintenance_work_mem, or the number of
* buffers usable for the index, whichever is less. (Limiting by the
* number of buffers should reduce thrashing between PG buffers and kernel
* buffers, which seems useful even if no physical I/O results. Limiting
* by maintenance_work_mem is useful to allow easy testing of the sort
* code path, and may be useful to DBAs as an additional control knob.)
*
* NOTE: this test will need adjustment if a bucket is ever different from
* one page. Also, "initial index size" accounting does not include the
* metapage, nor the first bitmap page.
*/
sort_threshold = (maintenance_work_mem * 1024L) / BLCKSZ;
if (index->rd_rel->relpersistence != RELPERSISTENCE_TEMP)
sort_threshold = Min(sort_threshold, NBuffers);
else
sort_threshold = Min(sort_threshold, NLocBuffer);
if (num_buckets >= (uint32) sort_threshold)
buildstate.spool = _h_spoolinit(heap, index, num_buckets);
else
buildstate.spool = NULL;
/* prepare to build the index */
buildstate.indtuples = 0;
buildstate.heapRel = heap;
/* do the heap scan */
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
hashbuildCallback, (void *) &buildstate);
if (buildstate.spool)
{
/* sort the tuples and insert them into the index */
_h_indexbuild(buildstate.spool, buildstate.heapRel);
_h_spooldestroy(buildstate.spool);
}
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
static Datum
pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo)
{
Datum result;
BlockNumber nblocks;
BlockNumber blkno;
BTIndexStat indexStat;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
/*
* Read metapage
*/
{
Buffer buffer = ReadBufferExtended(rel, MAIN_FORKNUM, 0, RBM_NORMAL, bstrategy);
Page page = BufferGetPage(buffer);
BTMetaPageData *metad = BTPageGetMeta(page);
indexStat.version = metad->btm_version;
indexStat.level = metad->btm_level;
indexStat.root_blkno = metad->btm_root;
ReleaseBuffer(buffer);
}
/* -- init counters -- */
indexStat.internal_pages = 0;
indexStat.leaf_pages = 0;
indexStat.empty_pages = 0;
indexStat.deleted_pages = 0;
indexStat.max_avail = 0;
indexStat.free_space = 0;
indexStat.fragments = 0;
/*
* Scan all blocks except the metapage
*/
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buffer;
Page page;
BTPageOpaque opaque;
CHECK_FOR_INTERRUPTS();
/* Read and lock buffer */
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/* Determine page type, and update totals */
if (P_ISDELETED(opaque))
indexStat.deleted_pages++;
else if (P_IGNORE(opaque))
indexStat.empty_pages++; /* this is the "half dead" state */
else if (P_ISLEAF(opaque))
{
int max_avail;
max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
indexStat.max_avail += max_avail;
indexStat.free_space += PageGetFreeSpace(page);
indexStat.leaf_pages++;
/*
* If the next leaf is on an earlier block, it means a
* fragmentation.
*/
if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
indexStat.fragments++;
}
else
indexStat.internal_pages++;
/* Unlock and release buffer */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
relation_close(rel, AccessShareLock);
/*----------------------------
* Build a result tuple
*----------------------------
*/
{
TupleDesc tupleDesc;
int j;
char *values[10];
HeapTuple tuple;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
j = 0;
values[j++] = psprintf("%d", indexStat.version);
values[j++] = psprintf("%d", indexStat.level);
values[j++] = psprintf(INT64_FORMAT,
(1 + /* include the metapage in index_size */
indexStat.leaf_pages +
indexStat.internal_pages +
indexStat.deleted_pages +
indexStat.empty_pages) * BLCKSZ);
values[j++] = psprintf("%u", indexStat.root_blkno);
values[j++] = psprintf(INT64_FORMAT, indexStat.internal_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.leaf_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.empty_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.deleted_pages);
if (indexStat.max_avail > 0)
values[j++] = psprintf("%.2f",
100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
else
values[j++] = pstrdup("NaN");
if (indexStat.leaf_pages > 0)
values[j++] = psprintf("%.2f",
(double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
else
values[j++] = pstrdup("NaN");
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
values);
result = HeapTupleGetDatum(tuple);
}
return result;
}
/*
* get_relation_info -
* Retrieves catalog information for a given relation.
*
* Given the Oid of the relation, return the following info into fields
* of the RelOptInfo struct:
*
* min_attr lowest valid AttrNumber
* max_attr highest valid AttrNumber
* indexlist list of IndexOptInfos for relation's indexes
* pages number of pages
* tuples number of tuples
*
* Also, initialize the attr_needed[] and attr_widths[] arrays. In most
* cases these are left as zeroes, but sometimes we need to compute attr
* widths here, and we may as well cache the results for costsize.c.
*
* If inhparent is true, all we need to do is set up the attr arrays:
* the RelOptInfo actually represents the appendrel formed by an inheritance
* tree, and so the parent rel's physical size and index information isn't
* important for it.
*/
void
get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
RelOptInfo *rel)
{
Index varno = rel->relid;
Relation relation;
bool hasindex;
List *indexinfos = NIL;
/*
* We need not lock the relation since it was already locked, either by
* the rewriter or when expand_inherited_rtentry() added it to the query's
* rangetable.
*/
relation = heap_open(relationObjectId, NoLock);
rel->min_attr = FirstLowInvalidHeapAttributeNumber + 1;
rel->max_attr = RelationGetNumberOfAttributes(relation);
rel->reltablespace = RelationGetForm(relation)->reltablespace;
Assert(rel->max_attr >= rel->min_attr);
rel->attr_needed = (Relids *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(Relids));
rel->attr_widths = (int32 *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(int32));
/*
* Estimate relation size --- unless it's an inheritance parent, in which
* case the size will be computed later in set_append_rel_pathlist, and we
* must leave it zero for now to avoid bollixing the total_table_pages
* calculation.
*/
if (!inhparent)
estimate_rel_size(relation, rel->attr_widths - rel->min_attr,
&rel->pages, &rel->tuples);
/*
* Make list of indexes. Ignore indexes on system catalogs if told to.
* Don't bother with indexes for an inheritance parent, either.
*/
if (inhparent ||
(IgnoreSystemIndexes && IsSystemClass(relation->rd_rel)))
hasindex = false;
else
hasindex = relation->rd_rel->relhasindex;
if (hasindex)
{
List *indexoidlist;
ListCell *l;
LOCKMODE lmode;
indexoidlist = RelationGetIndexList(relation);
/*
* For each index, we get the same type of lock that the executor will
* need, and do not release it. This saves a couple of trips to the
* shared lock manager while not creating any real loss of
* concurrency, because no schema changes could be happening on the
* index while we hold lock on the parent rel, and neither lock type
* blocks any other kind of index operation.
*/
if (rel->relid == root->parse->resultRelation)
lmode = RowExclusiveLock;
else
lmode = AccessShareLock;
foreach(l, indexoidlist)
{
Oid indexoid = lfirst_oid(l);
Relation indexRelation;
Form_pg_index index;
IndexOptInfo *info;
int ncolumns;
int i;
/*
* Extract info from the relation descriptor for the index.
*/
indexRelation = index_open(indexoid, lmode);
index = indexRelation->rd_index;
/*
* Ignore invalid indexes, since they can't safely be used for
* queries. Note that this is OK because the data structure we
* are constructing is only used by the planner --- the executor
* still needs to insert into "invalid" indexes!
*/
if (!index->indisvalid)
{
index_close(indexRelation, NoLock);
continue;
}
/*
* If the index is valid, but cannot yet be used, ignore it; but
* mark the plan we are generating as transient. See
* src/backend/access/heap/README.HOT for discussion.
*/
if (index->indcheckxmin &&
!TransactionIdPrecedes(HeapTupleHeaderGetXmin(indexRelation->rd_indextuple->t_data),
TransactionXmin))
{
root->glob->transientPlan = true;
index_close(indexRelation, NoLock);
continue;
}
info = makeNode(IndexOptInfo);
info->indexoid = index->indexrelid;
info->reltablespace =
RelationGetForm(indexRelation)->reltablespace;
info->rel = rel;
info->ncolumns = ncolumns = index->indnatts;
/*
* Allocate per-column info arrays. To save a few palloc cycles
* we allocate all the Oid-type arrays in one request. Note that
* the opfamily array needs an extra, terminating zero at the end.
* We pre-zero the ordering info in case the index is unordered.
*/
info->indexkeys = (int *) palloc(sizeof(int) * ncolumns);
info->opfamily = (Oid *) palloc0(sizeof(Oid) * (4 * ncolumns + 1));
info->opcintype = info->opfamily + (ncolumns + 1);
info->fwdsortop = info->opcintype + ncolumns;
info->revsortop = info->fwdsortop + ncolumns;
info->nulls_first = (bool *) palloc0(sizeof(bool) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
info->indexkeys[i] = index->indkey.values[i];
info->opfamily[i] = indexRelation->rd_opfamily[i];
info->opcintype[i] = indexRelation->rd_opcintype[i];
}
info->relam = indexRelation->rd_rel->relam;
info->amcostestimate = indexRelation->rd_am->amcostestimate;
info->amoptionalkey = indexRelation->rd_am->amoptionalkey;
info->amsearchnulls = indexRelation->rd_am->amsearchnulls;
info->amhasgettuple = OidIsValid(indexRelation->rd_am->amgettuple);
info->amhasgetbitmap = OidIsValid(indexRelation->rd_am->amgetbitmap);
/*
* Fetch the ordering operators associated with the index, if any.
* We expect that all ordering-capable indexes use btree's
* strategy numbers for the ordering operators.
*/
if (indexRelation->rd_am->amcanorder)
{
int nstrat = indexRelation->rd_am->amstrategies;
for (i = 0; i < ncolumns; i++)
{
int16 opt = indexRelation->rd_indoption[i];
int fwdstrat;
int revstrat;
if (opt & INDOPTION_DESC)
{
fwdstrat = BTGreaterStrategyNumber;
revstrat = BTLessStrategyNumber;
}
else
{
fwdstrat = BTLessStrategyNumber;
revstrat = BTGreaterStrategyNumber;
}
/*
* Index AM must have a fixed set of strategies for it to
* make sense to specify amcanorder, so we need not allow
* the case amstrategies == 0.
*/
if (fwdstrat > 0)
{
Assert(fwdstrat <= nstrat);
info->fwdsortop[i] = indexRelation->rd_operator[i * nstrat + fwdstrat - 1];
}
if (revstrat > 0)
{
Assert(revstrat <= nstrat);
info->revsortop[i] = indexRelation->rd_operator[i * nstrat + revstrat - 1];
}
info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
}
}
/*
* Fetch the index expressions and predicate, if any. We must
* modify the copies we obtain from the relcache to have the
* correct varno for the parent relation, so that they match up
* correctly against qual clauses.
*/
info->indexprs = RelationGetIndexExpressions(indexRelation);
info->indpred = RelationGetIndexPredicate(indexRelation);
if (info->indexprs && varno != 1)
ChangeVarNodes((Node *) info->indexprs, 1, varno, 0);
if (info->indpred && varno != 1)
ChangeVarNodes((Node *) info->indpred, 1, varno, 0);
info->predOK = false; /* set later in indxpath.c */
info->unique = index->indisunique;
/*
* Estimate the index size. If it's not a partial index, we lock
* the number-of-tuples estimate to equal the parent table; if it
* is partial then we have to use the same methods as we would for
* a table, except we can be sure that the index is not larger
* than the table.
*/
if (info->indpred == NIL)
{
info->pages = RelationGetNumberOfBlocks(indexRelation);
info->tuples = rel->tuples;
}
else
{
estimate_rel_size(indexRelation, NULL,
&info->pages, &info->tuples);
if (info->tuples > rel->tuples)
info->tuples = rel->tuples;
}
index_close(indexRelation, NoLock);
indexinfos = lcons(info, indexinfos);
}
list_free(indexoidlist);
}
/*
* lazy_truncate_heap - try to truncate off any empty pages at the end
*/
static void
lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats)
{
BlockNumber old_rel_pages = vacrelstats->rel_pages;
BlockNumber new_rel_pages;
PGRUsage ru0;
pg_rusage_init(&ru0);
/*
* We need full exclusive lock on the relation in order to do truncation.
* If we can't get it, give up rather than waiting --- we don't want to
* block other backends, and we don't want to deadlock (which is quite
* possible considering we already hold a lower-grade lock).
*/
if (!ConditionalLockRelation(onerel, AccessExclusiveLock))
return;
/*
* Now that we have exclusive lock, look to see if the rel has grown
* whilst we were vacuuming with non-exclusive lock. If so, give up; the
* newly added pages presumably contain non-deletable tuples.
*/
new_rel_pages = RelationGetNumberOfBlocks(onerel);
if (new_rel_pages != old_rel_pages)
{
/*
* Note: we intentionally don't update vacrelstats->rel_pages with the
* new rel size here. If we did, it would amount to assuming that the
* new pages are empty, which is unlikely. Leaving the numbers alone
* amounts to assuming that the new pages have the same tuple density
* as existing ones, which is less unlikely.
*/
UnlockRelation(onerel, AccessExclusiveLock);
return;
}
/*
* Scan backwards from the end to verify that the end pages actually
* contain no tuples. This is *necessary*, not optional, because other
* backends could have added tuples to these pages whilst we were
* vacuuming.
*/
new_rel_pages = count_nondeletable_pages(onerel, vacrelstats);
if (new_rel_pages >= old_rel_pages)
{
/* can't do anything after all */
UnlockRelation(onerel, AccessExclusiveLock);
return;
}
/*
* Okay to truncate.
*/
RelationTruncate(onerel, new_rel_pages);
/*
* We can release the exclusive lock as soon as we have truncated. Other
* backends can't safely access the relation until they have processed the
* smgr invalidation that smgrtruncate sent out ... but that should happen
* as part of standard invalidation processing once they acquire lock on
* the relation.
*/
UnlockRelation(onerel, AccessExclusiveLock);
/*
* Update statistics. Here, it *is* correct to adjust rel_pages without
* also touching reltuples, since the tuple count wasn't changed by the
* truncation.
*/
vacrelstats->rel_pages = new_rel_pages;
vacrelstats->pages_removed = old_rel_pages - new_rel_pages;
ereport(elevel,
(errmsg("\"%s\": truncated %u to %u pages",
RelationGetRelationName(onerel),
old_rel_pages, new_rel_pages),
errdetail("%s.",
pg_rusage_show(&ru0))));
}
/*
* btvacuumscan --- scan the index for VACUUMing purposes
*
* This combines the functions of looking for leaf tuples that are deletable
* according to the vacuum callback, looking for empty pages that can be
* deleted, and looking for old deleted pages that can be recycled. Both
* btbulkdelete and btvacuumcleanup invoke this (the latter only if no
* btbulkdelete call occurred).
*
* The caller is responsible for initially allocating/zeroing a stats struct
* and for obtaining a vacuum cycle ID if necessary.
*/
static void
btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback, void *callback_state,
BTCycleId cycleid)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
Relation rel = info->index;
BTVacState vstate;
BlockNumber num_pages;
BlockNumber blkno;
bool needLock;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
/*
* Reset counts that will be incremented during the scan; needed in case
* of multiple scans during a single VACUUM command
*/
stats->num_index_tuples = 0;
stats->pages_deleted = 0;
/* Set up info to pass down to btvacuumpage */
vstate.info = info;
vstate.stats = stats;
vstate.callback = callback;
vstate.callback_state = callback_state;
vstate.cycleid = cycleid;
vstate.freePages = NULL; /* temporarily */
vstate.nFreePages = 0;
vstate.maxFreePages = 0;
vstate.totFreePages = 0;
/* Create a temporary memory context to run _bt_pagedel in */
vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
"_bt_pagedel",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
/*
* The outer loop iterates over all index pages except the metapage, in
* physical order (we hope the kernel will cooperate in providing
* read-ahead for speed). It is critical that we visit all leaf pages,
* including ones added after we start the scan, else we might fail to
* delete some deletable tuples. Hence, we must repeatedly check the
* relation length. We must acquire the relation-extension lock while
* doing so to avoid a race condition: if someone else is extending the
* relation, there is a window where bufmgr/smgr have created a new
* all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
* we manage to scan such a page here, we'll improperly assume it can be
* recycled. Taking the lock synchronizes things enough to prevent a
* problem: either num_pages won't include the new page, or _bt_getbuf
* already has write lock on the buffer and it will be fully initialized
* before we can examine it. (See also vacuumlazy.c, which has the same
* issue.) Also, we need not worry if a page is added immediately after
* we look; the page splitting code already has write-lock on the left
* page before it adds a right page, so we must already have processed any
* tuples due to be moved into such a page.
*
* We can skip locking for new or temp relations, however, since no one
* else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
blkno = BTREE_METAPAGE + 1;
for (;;)
{
/* Get the current relation length */
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
num_pages = RelationGetNumberOfBlocks(rel);
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Allocate freePages after we read num_pages the first time */
if (vstate.freePages == NULL)
{
/* No point in remembering more than MaxFSMPages pages */
vstate.maxFreePages = MaxFSMPages;
if ((BlockNumber) vstate.maxFreePages > num_pages)
vstate.maxFreePages = (int) num_pages;
vstate.freePages = (BlockNumber *)
palloc(vstate.maxFreePages * sizeof(BlockNumber));
}
/* Quit if we've scanned the whole relation */
if (blkno >= num_pages)
break;
/* Iterate over pages, then loop back to recheck length */
for (; blkno < num_pages; blkno++)
{
btvacuumpage(&vstate, blkno, blkno);
}
}
/*
* During VACUUM FULL, we truncate off any recyclable pages at the end of
* the index. In a normal vacuum it'd be unsafe to do this except by
* acquiring exclusive lock on the index and then rechecking all the
* pages; doesn't seem worth it.
*/
if (info->vacuum_full && vstate.nFreePages > 0)
{
BlockNumber new_pages = num_pages;
while (vstate.nFreePages > 0 &&
vstate.freePages[vstate.nFreePages - 1] == new_pages - 1)
{
new_pages--;
stats->pages_deleted--;
vstate.nFreePages--;
vstate.totFreePages = vstate.nFreePages; /* can't be more */
}
if (new_pages != num_pages)
{
/*
* Okay to truncate.
*/
RelationTruncate(rel, new_pages,
/* markPersistentAsPhysicallyTruncated */ true);
/* update statistics */
stats->pages_removed += num_pages - new_pages;
num_pages = new_pages;
}
}
/*
* Update the shared Free Space Map with the info we now have about free
* pages in the index, discarding any old info the map may have. We do not
* need to sort the page numbers; they're in order already.
*/
RecordIndexFreeSpace(&rel->rd_node, vstate.totFreePages,
vstate.nFreePages, vstate.freePages);
pfree(vstate.freePages);
MemoryContextDelete(vstate.pagedelcontext);
/* update statistics */
stats->num_pages = num_pages;
stats->pages_free = vstate.totFreePages;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
}
/*
* btbuild() -- build a new btree index.
*/
IndexBuildResult *
btbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
BTBuildState buildstate;
buildstate.isUnique = indexInfo->ii_Unique;
buildstate.haveDead = false;
buildstate.heapRel = heap;
buildstate.spool = NULL;
buildstate.spool2 = NULL;
buildstate.indtuples = 0;
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
ResetUsage();
#endif /* BTREE_BUILD_STATS */
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
buildstate.spool = _bt_spoolinit(heap, index, indexInfo->ii_Unique, false);
/*
* If building a unique index, put dead tuples in a second spool to keep
* them out of the uniqueness check.
*/
if (indexInfo->ii_Unique)
buildstate.spool2 = _bt_spoolinit(heap, index, false, true);
/* do the heap scan */
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
btbuildCallback, (void *) &buildstate);
/* okay, all heap tuples are indexed */
if (buildstate.spool2 && !buildstate.haveDead)
{
/* spool2 turns out to be unnecessary */
_bt_spooldestroy(buildstate.spool2);
buildstate.spool2 = NULL;
}
/*
* Finish the build by (1) completing the sort of the spool file, (2)
* inserting the sorted tuples into btree pages and (3) building the upper
* levels.
*/
_bt_leafbuild(buildstate.spool, buildstate.spool2);
_bt_spooldestroy(buildstate.spool);
if (buildstate.spool2)
_bt_spooldestroy(buildstate.spool2);
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
{
ShowUsage("BTREE BUILD STATS");
ResetUsage();
}
#endif /* BTREE_BUILD_STATS */
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
/*
* For a newly inserted heap tid, check if an entry with this tid
* already exists in a unique index. If it does, abort the inserting
* transaction.
*/
static void
_bt_validate_tid(Relation irel, ItemPointer h_tid)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber blkno;
BlockNumber num_pages;
Buffer buf;
Page page;
BTPageOpaque opaque;
IndexTuple itup;
OffsetNumber maxoff,
minoff,
offnum;
elog(DEBUG1, "validating tid (%d,%d) for index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
RelationGetRelationName(irel));
blkno = BTREE_METAPAGE + 1;
num_pages = RelationGetNumberOfBlocks(irel);
MIRROREDLOCK_BUFMGR_LOCK;
for (; blkno < num_pages; blkno++)
{
buf = ReadBuffer(irel, blkno);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!PageIsNew(page))
_bt_checkpage(irel, buf);
if (P_ISLEAF(opaque))
{
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
if (ItemPointerEquals(&itup->t_tid, h_tid))
{
Form_pg_attribute key_att = RelationGetDescr(irel)->attrs[0];
Oid key = InvalidOid;
bool isnull;
if (key_att->atttypid == OIDOID)
{
key = DatumGetInt32(
index_getattr(itup, 1, RelationGetDescr(irel), &isnull));
elog(ERROR, "found tid (%d,%d), %s (%d) already in index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
NameStr(key_att->attname), key, RelationGetRelationName(irel));
}
else
{
elog(ERROR, "found tid (%d,%d) already in index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
RelationGetRelationName(irel));
}
}
}
}
ReleaseBuffer(buf);
}
MIRROREDLOCK_BUFMGR_UNLOCK;
}
/*
* hashbuild() -- build a new hash index.
*/
IndexBuildResult *
hashbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
BlockNumber relpages;
double reltuples;
double allvisfrac;
uint32 num_buckets;
HashBuildState buildstate;
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* Estimate the number of rows currently present in the table */
estimate_rel_size(heap, NULL, &relpages, &reltuples, &allvisfrac);
/* Initialize the hash index metadata page and initial buckets */
num_buckets = _hash_metapinit(index, reltuples, MAIN_FORKNUM);
/*
* If we just insert the tuples into the index in scan order, then
* (assuming their hash codes are pretty random) there will be no locality
* of access to the index, and if the index is bigger than available RAM
* then we'll thrash horribly. To prevent that scenario, we can sort the
* tuples by (expected) bucket number. However, such a sort is useless
* overhead when the index does fit in RAM. We choose to sort if the
* initial index size exceeds NBuffers.
*
* NOTE: this test will need adjustment if a bucket is ever different from
* one page.
*/
if (num_buckets >= (uint32) NBuffers)
buildstate.spool = _h_spoolinit(heap, index, num_buckets);
else
buildstate.spool = NULL;
/* prepare to build the index */
buildstate.indtuples = 0;
/* do the heap scan */
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
hashbuildCallback, (void *) &buildstate);
if (buildstate.spool)
{
/* sort the tuples and insert them into the index */
_h_indexbuild(buildstate.spool);
_h_spooldestroy(buildstate.spool);
}
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
/*
* This function takes an already open relation and scans its pages,
* skipping those that have the corresponding visibility map bit set.
* For pages we skip, we find the free space from the free space map
* and approximate tuple_len on that basis. For the others, we count
* the exact number of dead tuples etc.
*
* This scan is loosely based on vacuumlazy.c:lazy_scan_heap(), but
* we do not try to avoid skipping single pages.
*/
static void
statapprox_heap(Relation rel, output_type *stat)
{
BlockNumber scanned,
nblocks,
blkno;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy;
TransactionId OldestXmin;
uint64 misc_count = 0;
OldestXmin = GetOldestXmin(rel, PROCARRAY_FLAGS_VACUUM);
bstrategy = GetAccessStrategy(BAS_BULKREAD);
nblocks = RelationGetNumberOfBlocks(rel);
scanned = 0;
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
Size freespace;
CHECK_FOR_INTERRUPTS();
/*
* If the page has only visible tuples, then we can find out the free
* space from the FSM and move on.
*/
if (VM_ALL_VISIBLE(rel, blkno, &vmbuffer))
{
freespace = GetRecordedFreeSpace(rel, blkno);
stat->tuple_len += BLCKSZ - freespace;
stat->free_space += freespace;
continue;
}
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno,
RBM_NORMAL, bstrategy);
LockBuffer(buf, BUFFER_LOCK_SHARE);
page = BufferGetPage(buf);
/*
* It's not safe to call PageGetHeapFreeSpace() on new pages, so we
* treat them as being free space for our purposes.
*/
if (!PageIsNew(page))
stat->free_space += PageGetHeapFreeSpace(page);
else
stat->free_space += BLCKSZ - SizeOfPageHeaderData;
if (PageIsNew(page) || PageIsEmpty(page))
{
UnlockReleaseBuffer(buf);
continue;
}
scanned++;
/*
* Look at each tuple on the page and decide whether it's live or
* dead, then count it and its size. Unlike lazy_scan_heap, we can
* afford to ignore problems and special cases.
*/
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
HeapTupleData tuple;
itemid = PageGetItemId(page, offnum);
if (!ItemIdIsUsed(itemid) || ItemIdIsRedirected(itemid) ||
ItemIdIsDead(itemid))
{
continue;
}
Assert(ItemIdIsNormal(itemid));
ItemPointerSet(&(tuple.t_self), blkno, offnum);
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tuple.t_tableOid = RelationGetRelid(rel);
/*
* We count live and dead tuples, but we also need to add up
* others in order to feed vac_estimate_reltuples.
*/
switch (HeapTupleSatisfiesVacuum(&tuple, OldestXmin, buf))
{
case HEAPTUPLE_RECENTLY_DEAD:
misc_count++;
/* Fall through */
case HEAPTUPLE_DEAD:
stat->dead_tuple_len += tuple.t_len;
stat->dead_tuple_count++;
break;
case HEAPTUPLE_LIVE:
stat->tuple_len += tuple.t_len;
stat->tuple_count++;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
case HEAPTUPLE_DELETE_IN_PROGRESS:
misc_count++;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
}
UnlockReleaseBuffer(buf);
}
stat->table_len = (uint64) nblocks *BLCKSZ;
stat->tuple_count = vac_estimate_reltuples(rel, false, nblocks, scanned,
stat->tuple_count + misc_count);
/*
* Calculate percentages if the relation has one or more pages.
*/
if (nblocks != 0)
{
stat->scanned_percent = 100 * scanned / nblocks;
stat->tuple_percent = 100.0 * stat->tuple_len / stat->table_len;
stat->dead_tuple_percent = 100.0 * stat->dead_tuple_len / stat->table_len;
stat->free_percent = 100.0 * stat->free_space / stat->table_len;
}
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
}
/*
* Insert all matching tuples into to a bitmap.
*/
int64
blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
{
int64 ntids = 0;
BlockNumber blkno = BLOOM_HEAD_BLKNO,
npages;
int i;
BufferAccessStrategy bas;
BloomScanOpaque so = (BloomScanOpaque) scan->opaque;
if (so->sign == NULL)
{
/* New search: have to calculate search signature */
ScanKey skey = scan->keyData;
so->sign = palloc0(sizeof(SignType) * so->state.opts.bloomLength);
for (i = 0; i < scan->numberOfKeys; i++)
{
/*
* Assume bloom-indexable operators to be strict, so nothing could
* be found for NULL key.
*/
if (skey->sk_flags & SK_ISNULL)
{
pfree(so->sign);
so->sign = NULL;
return 0;
}
/* Add next value to the signature */
signValue(&so->state, so->sign, skey->sk_argument,
skey->sk_attno - 1);
skey++;
}
}
/*
* We're going to read the whole index. This is why we use appropriate
* buffer access strategy.
*/
bas = GetAccessStrategy(BAS_BULKREAD);
npages = RelationGetNumberOfBlocks(scan->indexRelation);
for (blkno = BLOOM_HEAD_BLKNO; blkno < npages; blkno++)
{
Buffer buffer;
Page page;
buffer = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM,
blkno, RBM_NORMAL, bas);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
TestForOldSnapshot(scan->xs_snapshot, scan->indexRelation, page);
if (!BloomPageIsDeleted(page))
{
OffsetNumber offset,
maxOffset = BloomPageGetMaxOffset(page);
for (offset = 1; offset <= maxOffset; offset++)
{
BloomTuple *itup = BloomPageGetTuple(&so->state, page, offset);
bool res = true;
/* Check index signature with scan signature */
for (i = 0; i < so->state.opts.bloomLength; i++)
{
if ((itup->sign[i] & so->sign[i]) != so->sign[i])
{
res = false;
break;
}
}
/* Add matching tuples to bitmap */
if (res)
{
tbm_add_tuples(tbm, &itup->heapPtr, 1, true);
ntids++;
}
}
}
UnlockReleaseBuffer(buffer);
CHECK_FOR_INTERRUPTS();
}
FreeAccessStrategy(bas);
return ntids;
}
/*
* VACUUM cleanup: update FSM
*/
IndexBulkDeleteResult *
gistvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
{
Relation rel = info->index;
BlockNumber npages,
blkno;
BlockNumber totFreePages;
bool needLock;
/* No-op in ANALYZE ONLY mode */
if (info->analyze_only)
return stats;
/* Set up all-zero stats if gistbulkdelete wasn't called */
if (stats == NULL)
{
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
/* use heap's tuple count */
stats->num_index_tuples = info->num_heap_tuples;
stats->estimated_count = info->estimated_count;
/*
* XXX the above is wrong if index is partial. Would it be OK to just
* return NULL, or is there work we must do below?
*/
}
/*
* Need lock unless it's local to this backend.
*/
needLock = !RELATION_IS_LOCAL(rel);
/* try to find deleted pages */
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
npages = RelationGetNumberOfBlocks(rel);
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
totFreePages = 0;
for (blkno = GIST_ROOT_BLKNO + 1; blkno < npages; blkno++)
{
Buffer buffer;
Page page;
vacuum_delay_point();
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
info->strategy);
LockBuffer(buffer, GIST_SHARE);
page = (Page) BufferGetPage(buffer);
if (PageIsNew(page) || GistPageIsDeleted(page))
{
totFreePages++;
RecordFreeIndexPage(rel, blkno);
}
UnlockReleaseBuffer(buffer);
}
/* Finally, vacuum the FSM */
IndexFreeSpaceMapVacuum(info->index);
/* return statistics */
stats->pages_free = totFreePages;
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
stats->num_pages = RelationGetNumberOfBlocks(rel);
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
return stats;
}
/*
* Post vacuum, iterate over all entries in index, check if the h_tid
* of each entry exists and is not dead. For specific system tables,
* also ensure that the key in index entry matches the corresponding
* attribute in the heap tuple.
*/
void
_bt_validate_vacuum(Relation irel, Relation hrel, TransactionId oldest_xmin)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber blkno;
BlockNumber num_pages;
Buffer ibuf = InvalidBuffer;
Buffer hbuf = InvalidBuffer;
Page ipage;
BTPageOpaque opaque;
IndexTuple itup;
HeapTupleData htup;
OffsetNumber maxoff,
minoff,
offnum;
Oid ioid,
hoid;
bool isnull;
blkno = BTREE_METAPAGE + 1;
num_pages = RelationGetNumberOfBlocks(irel);
elog(LOG, "btvalidatevacuum: index %s, heap %s",
RelationGetRelationName(irel), RelationGetRelationName(hrel));
MIRROREDLOCK_BUFMGR_LOCK;
for (; blkno < num_pages; blkno++)
{
ibuf = ReadBuffer(irel, blkno);
ipage = BufferGetPage(ibuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(ipage);
if (!PageIsNew(ipage))
_bt_checkpage(irel, ibuf);
if (P_ISLEAF(opaque))
{
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(ipage);
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
itup = (IndexTuple) PageGetItem(ipage,
PageGetItemId(ipage, offnum));
ItemPointerCopy(&itup->t_tid, &htup.t_self);
/*
* TODO: construct a tid bitmap based on index tids
* and fetch heap tids in order afterwards. That will
* also allow validating if a heap tid appears twice
* in a unique index.
*/
if (!heap_release_fetch(hrel, SnapshotAny, &htup,
&hbuf, true, NULL))
{
elog(ERROR, "btvalidatevacuum: tid (%d,%d) from index %s "
"not found in heap %s",
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel),
RelationGetRelationName(hrel));
}
switch (HeapTupleSatisfiesVacuum(hrel, htup.t_data, oldest_xmin, hbuf))
{
case HEAPTUPLE_RECENTLY_DEAD:
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* these tuples are considered alive by vacuum */
break;
case HEAPTUPLE_DEAD:
elog(ERROR, "btvalidatevacuum: vacuum did not remove "
"dead tuple (%d,%d) from heap %s and index %s",
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(hrel),
RelationGetRelationName(irel));
break;
default:
elog(ERROR, "btvalidatevacuum: invalid visibility");
break;
}
switch(RelationGetRelid(irel))
{
case DatabaseOidIndexId:
case TypeOidIndexId:
case ClassOidIndexId:
case ConstraintOidIndexId:
hoid = HeapTupleGetOid(&htup);
ioid = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
if (hoid != ioid)
{
elog(ERROR,
"btvalidatevacuum: index oid(%d) != heap oid(%d)"
" tuple (%d,%d) index %s", ioid, hoid,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
break;
case GpRelationNodeOidIndexId:
hoid = heap_getattr(&htup, 1, RelationGetDescr(hrel), &isnull);
ioid = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
if (hoid != ioid)
{
elog(ERROR,
"btvalidatevacuum: index oid(%d) != heap oid(%d)"
" tuple (%d,%d) index %s", ioid, hoid,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
int4 hsegno = heap_getattr(&htup, 2, RelationGetDescr(hrel), &isnull);
int4 isegno = index_getattr(itup, 2, RelationGetDescr(irel), &isnull);
if (isegno != hsegno)
{
elog(ERROR,
"btvalidatevacuum: index segno(%d) != heap segno(%d)"
" tuple (%d,%d) index %s", isegno, hsegno,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
break;
default:
break;
}
if (RelationGetNamespace(irel) == PG_AOSEGMENT_NAMESPACE)
{
int4 isegno = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
int4 hsegno = heap_getattr(&htup, 1, RelationGetDescr(hrel), &isnull);
if (isegno != hsegno)
{
elog(ERROR,
"btvalidatevacuum: index segno(%d) != heap segno(%d)"
" tuple (%d,%d) index %s", isegno, hsegno,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
}
}
}
if (BufferIsValid(ibuf))
ReleaseBuffer(ibuf);
}
if (BufferIsValid(hbuf))
ReleaseBuffer(hbuf);
MIRROREDLOCK_BUFMGR_UNLOCK;
}
/* ------------------------------------------------------
* pgstathashindex()
*
* Usage: SELECT * FROM pgstathashindex('hashindex');
* ------------------------------------------------------
*/
Datum
pgstathashindex(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
BlockNumber nblocks;
BlockNumber blkno;
Relation rel;
HashIndexStat stats;
BufferAccessStrategy bstrategy;
HeapTuple tuple;
TupleDesc tupleDesc;
Datum values[8];
bool nulls[8];
Buffer metabuf;
HashMetaPage metap;
float8 free_percent;
uint64 total_space;
rel = index_open(relid, AccessShareLock);
/* index_open() checks that it's an index */
if (!IS_HASH(rel))
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("relation \"%s\" is not a HASH index",
RelationGetRelationName(rel))));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary indexes of other sessions")));
/* Get the information we need from the metapage. */
memset(&stats, 0, sizeof(stats));
metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
metap = HashPageGetMeta(BufferGetPage(metabuf));
stats.version = metap->hashm_version;
stats.space_per_page = metap->hashm_bsize;
_hash_relbuf(rel, metabuf);
/* Get the current relation length */
nblocks = RelationGetNumberOfBlocks(rel);
/* prepare access strategy for this index */
bstrategy = GetAccessStrategy(BAS_BULKREAD);
/* Start from blkno 1 as 0th block is metapage */
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
CHECK_FOR_INTERRUPTS();
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
bstrategy);
LockBuffer(buf, BUFFER_LOCK_SHARE);
page = (Page) BufferGetPage(buf);
if (PageIsNew(page))
stats.unused_pages++;
else if (PageGetSpecialSize(page) !=
MAXALIGN(sizeof(HashPageOpaqueData)))
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" contains corrupted page at block %u",
RelationGetRelationName(rel),
BufferGetBlockNumber(buf))));
else
{
HashPageOpaque opaque;
int pagetype;
opaque = (HashPageOpaque) PageGetSpecialPointer(page);
pagetype = opaque->hasho_flag & LH_PAGE_TYPE;
if (pagetype == LH_BUCKET_PAGE)
{
stats.bucket_pages++;
GetHashPageStats(page, &stats);
}
else if (pagetype == LH_OVERFLOW_PAGE)
{
stats.overflow_pages++;
GetHashPageStats(page, &stats);
}
else if (pagetype == LH_BITMAP_PAGE)
stats.bitmap_pages++;
else if (pagetype == LH_UNUSED_PAGE)
stats.unused_pages++;
else
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("unexpected page type 0x%04X in HASH index \"%s\" block %u",
opaque->hasho_flag, RelationGetRelationName(rel),
BufferGetBlockNumber(buf))));
}
UnlockReleaseBuffer(buf);
}
/* Done accessing the index */
index_close(rel, AccessShareLock);
/* Count unused pages as free space. */
stats.free_space += stats.unused_pages * stats.space_per_page;
/*
* Total space available for tuples excludes the metapage and the bitmap
* pages.
*/
total_space = (nblocks - (stats.bitmap_pages + 1)) * stats.space_per_page;
if (total_space == 0)
free_percent = 0.0;
else
free_percent = 100.0 * stats.free_space / total_space;
/*
* Build a tuple descriptor for our result type
*/
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
tupleDesc = BlessTupleDesc(tupleDesc);
/*
* Build and return the tuple
*/
MemSet(nulls, 0, sizeof(nulls));
values[0] = Int32GetDatum(stats.version);
values[1] = Int64GetDatum((int64) stats.bucket_pages);
values[2] = Int64GetDatum((int64) stats.overflow_pages);
values[3] = Int64GetDatum((int64) stats.bitmap_pages);
values[4] = Int64GetDatum((int64) stats.unused_pages);
values[5] = Int64GetDatum(stats.live_items);
values[6] = Int64GetDatum(stats.dead_items);
values[7] = Float8GetDatum(free_percent);
tuple = heap_form_tuple(tupleDesc, values, nulls);
PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
}
/*
* btbuild() -- build a new btree index.
*/
Datum
btbuild(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
Relation heap = (Relation) PG_GETARG_POINTER(0);
Relation index = (Relation) PG_GETARG_POINTER(1);
IndexInfo *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
IndexBuildResult *result;
double reltuples;
BTBuildState buildstate;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
buildstate.isUnique = indexInfo->ii_Unique;
buildstate.haveDead = false;
buildstate.heapRel = heap;
buildstate.spool = NULL;
buildstate.spool2 = NULL;
buildstate.indtuples = 0;
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
ResetUsage();
#endif /* BTREE_BUILD_STATS */
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
PG_TRY();
{
buildstate.spool = _bt_spoolinit(index, indexInfo->ii_Unique, false);
/*
* If building a unique index, put dead tuples in a second spool to keep
* them out of the uniqueness check.
*/
if (indexInfo->ii_Unique)
buildstate.spool2 = _bt_spoolinit(index, false, true);
/* do the heap scan */
reltuples = IndexBuildScan(heap, index, indexInfo, false,
btbuildCallback, (void *) &buildstate);
/* okay, all heap tuples are indexed */
if (buildstate.spool2 && !buildstate.haveDead)
{
/* spool2 turns out to be unnecessary */
_bt_spooldestroy(buildstate.spool2);
buildstate.spool2 = NULL;
}
/*
* Finish the build by (1) completing the sort of the spool file, (2)
* inserting the sorted tuples into btree pages and (3) building the upper
* levels.
*/
_bt_leafbuild(buildstate.spool, buildstate.spool2);
_bt_spooldestroy(buildstate.spool);
buildstate.spool = NULL;
if (buildstate.spool2)
{
_bt_spooldestroy(buildstate.spool2);
buildstate.spool2 = NULL;
}
}
PG_CATCH();
{
/* Clean up the sort state on error */
if (buildstate.spool)
{
_bt_spooldestroy(buildstate.spool);
buildstate.spool = NULL;
}
if (buildstate.spool2)
{
_bt_spooldestroy(buildstate.spool2);
buildstate.spool2 = NULL;
}
PG_RE_THROW();
}
PG_END_TRY();
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
{
ShowUsage("BTREE BUILD STATS");
ResetUsage();
}
#endif /* BTREE_BUILD_STATS */
/*
* If we are reindexing a pre-existing index, it is critical to send out a
* relcache invalidation SI message to ensure all backends re-read the
* index metapage. We expect that the caller will ensure that happens
* (typically as a side effect of updating index stats, but it must happen
* even if the stats don't change!)
*/
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_POINTER(result);
}
Datum
ginbuild(PG_FUNCTION_ARGS)
{
Relation heap = (Relation) PG_GETARG_POINTER(0);
Relation index = (Relation) PG_GETARG_POINTER(1);
IndexInfo *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
IndexBuildResult *result;
double reltuples;
GinBuildState buildstate;
Buffer RootBuffer,
MetaBuffer;
ItemPointerData *list;
Datum key;
GinNullCategory category;
uint32 nlist;
MemoryContext oldCtx;
OffsetNumber attnum;
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
initGinState(&buildstate.ginstate, index);
buildstate.indtuples = 0;
memset(&buildstate.buildStats, 0, sizeof(GinStatsData));
/* initialize the meta page */
MetaBuffer = GinNewBuffer(index);
/* initialize the root page */
RootBuffer = GinNewBuffer(index);
START_CRIT_SECTION();
GinInitMetabuffer(MetaBuffer);
MarkBufferDirty(MetaBuffer);
GinInitBuffer(RootBuffer, GIN_LEAF);
MarkBufferDirty(RootBuffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
XLogRecData rdata;
Page page;
rdata.buffer = InvalidBuffer;
rdata.data = (char *) &(index->rd_node);
rdata.len = sizeof(RelFileNode);
rdata.next = NULL;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_INDEX, &rdata);
page = BufferGetPage(RootBuffer);
PageSetLSN(page, recptr);
page = BufferGetPage(MetaBuffer);
PageSetLSN(page, recptr);
}
UnlockReleaseBuffer(MetaBuffer);
UnlockReleaseBuffer(RootBuffer);
END_CRIT_SECTION();
/* count the root as first entry page */
buildstate.buildStats.nEntryPages++;
/*
* create a temporary memory context that is reset once for each tuple
* inserted into the index
*/
buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Gin build temporary context",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
buildstate.funcCtx = AllocSetContextCreate(buildstate.tmpCtx,
"Gin build temporary context for user-defined function",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
buildstate.accum.ginstate = &buildstate.ginstate;
ginInitBA(&buildstate.accum);
/*
* Do the heap scan. We disallow sync scan here because dataPlaceToPage
* prefers to receive tuples in TID order.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, false,
ginBuildCallback, (void *) &buildstate);
/* dump remaining entries to the index */
oldCtx = MemoryContextSwitchTo(buildstate.tmpCtx);
ginBeginBAScan(&buildstate.accum);
while ((list = ginGetBAEntry(&buildstate.accum,
&attnum, &key, &category, &nlist)) != NULL)
{
/* there could be many entries, so be willing to abort here */
CHECK_FOR_INTERRUPTS();
ginEntryInsert(&buildstate.ginstate, attnum, key, category,
list, nlist, &buildstate.buildStats);
}
MemoryContextSwitchTo(oldCtx);
MemoryContextDelete(buildstate.tmpCtx);
/*
* Update metapage stats
*/
buildstate.buildStats.nTotalPages = RelationGetNumberOfBlocks(index);
ginUpdateStats(index, &buildstate.buildStats);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
PG_RETURN_POINTER(result);
}
IndexBuildResult *
ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
GinBuildState buildstate;
Buffer RootBuffer,
MetaBuffer;
ItemPointerData *list;
Datum key;
GinNullCategory category;
uint32 nlist;
MemoryContext oldCtx;
OffsetNumber attnum;
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
initGinState(&buildstate.ginstate, index);
buildstate.indtuples = 0;
memset(&buildstate.buildStats, 0, sizeof(GinStatsData));
/* initialize the meta page */
MetaBuffer = GinNewBuffer(index);
/* initialize the root page */
RootBuffer = GinNewBuffer(index);
START_CRIT_SECTION();
GinInitMetabuffer(MetaBuffer);
MarkBufferDirty(MetaBuffer);
GinInitBuffer(RootBuffer, GIN_LEAF);
MarkBufferDirty(RootBuffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
Page page;
XLogBeginInsert();
XLogRegisterBuffer(0, MetaBuffer, REGBUF_WILL_INIT | REGBUF_STANDARD);
XLogRegisterBuffer(1, RootBuffer, REGBUF_WILL_INIT);
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_INDEX);
page = BufferGetPage(RootBuffer);
PageSetLSN(page, recptr);
page = BufferGetPage(MetaBuffer);
PageSetLSN(page, recptr);
}
UnlockReleaseBuffer(MetaBuffer);
UnlockReleaseBuffer(RootBuffer);
END_CRIT_SECTION();
/* count the root as first entry page */
buildstate.buildStats.nEntryPages++;
/*
* create a temporary memory context that is used to hold data not yet
* dumped out to the index
*/
buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Gin build temporary context",
ALLOCSET_DEFAULT_SIZES);
/*
* create a temporary memory context that is used for calling
* ginExtractEntries(), and can be reset after each tuple
*/
buildstate.funcCtx = AllocSetContextCreate(CurrentMemoryContext,
"Gin build temporary context for user-defined function",
ALLOCSET_DEFAULT_SIZES);
buildstate.accum.ginstate = &buildstate.ginstate;
ginInitBA(&buildstate.accum);
/*
* Do the heap scan. We disallow sync scan here because dataPlaceToPage
* prefers to receive tuples in TID order.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, false,
ginBuildCallback, (void *) &buildstate, NULL);
/* dump remaining entries to the index */
oldCtx = MemoryContextSwitchTo(buildstate.tmpCtx);
ginBeginBAScan(&buildstate.accum);
while ((list = ginGetBAEntry(&buildstate.accum,
&attnum, &key, &category, &nlist)) != NULL)
{
/* there could be many entries, so be willing to abort here */
CHECK_FOR_INTERRUPTS();
ginEntryInsert(&buildstate.ginstate, attnum, key, category,
list, nlist, &buildstate.buildStats);
}
MemoryContextSwitchTo(oldCtx);
MemoryContextDelete(buildstate.funcCtx);
MemoryContextDelete(buildstate.tmpCtx);
/*
* Update metapage stats
*/
buildstate.buildStats.nTotalPages = RelationGetNumberOfBlocks(index);
ginUpdateStats(index, &buildstate.buildStats);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
Datum
ginvacuumcleanup(PG_FUNCTION_ARGS)
{
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
Relation index = info->index;
bool needLock;
BlockNumber npages,
blkno;
BlockNumber totFreePages;
GinState ginstate;
GinStatsData idxStat;
/*
* In an autovacuum analyze, we want to clean up pending insertions.
* Otherwise, an ANALYZE-only call is a no-op.
*/
if (info->analyze_only)
{
if (IsAutoVacuumWorkerProcess())
{
initGinState(&ginstate, index);
ginInsertCleanup(&ginstate, true, stats);
}
PG_RETURN_POINTER(stats);
}
/*
* Set up all-zero stats and cleanup pending inserts if ginbulkdelete
* wasn't called
*/
if (stats == NULL)
{
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
initGinState(&ginstate, index);
ginInsertCleanup(&ginstate, true, stats);
}
memset(&idxStat, 0, sizeof(idxStat));
/*
* XXX we always report the heap tuple count as the number of index
* entries. This is bogus if the index is partial, but it's real hard to
* tell how many distinct heap entries are referenced by a GIN index.
*/
stats->num_index_tuples = info->num_heap_tuples;
stats->estimated_count = info->estimated_count;
/*
* Need lock unless it's local to this backend.
*/
needLock = !RELATION_IS_LOCAL(index);
if (needLock)
LockRelationForExtension(index, ExclusiveLock);
npages = RelationGetNumberOfBlocks(index);
if (needLock)
UnlockRelationForExtension(index, ExclusiveLock);
totFreePages = 0;
for (blkno = GIN_ROOT_BLKNO; blkno < npages; blkno++)
{
Buffer buffer;
Page page;
vacuum_delay_point();
buffer = ReadBufferExtended(index, MAIN_FORKNUM, blkno,
RBM_NORMAL, info->strategy);
LockBuffer(buffer, GIN_SHARE);
page = (Page) BufferGetPage(buffer);
if (GinPageIsDeleted(page))
{
Assert(blkno != GIN_ROOT_BLKNO);
RecordFreeIndexPage(index, blkno);
totFreePages++;
}
else if (GinPageIsData(page))
{
idxStat.nDataPages++;
}
else if (!GinPageIsList(page))
{
idxStat.nEntryPages++;
if (GinPageIsLeaf(page))
idxStat.nEntries += PageGetMaxOffsetNumber(page);
}
UnlockReleaseBuffer(buffer);
}
/* Update the metapage with accurate page and entry counts */
idxStat.nTotalPages = npages;
ginUpdateStats(info->index, &idxStat);
/* Finally, vacuum the FSM */
IndexFreeSpaceMapVacuum(info->index);
stats->pages_free = totFreePages;
if (needLock)
LockRelationForExtension(index, ExclusiveLock);
stats->num_pages = RelationGetNumberOfBlocks(index);
if (needLock)
UnlockRelationForExtension(index, ExclusiveLock);
PG_RETURN_POINTER(stats);
}
/*
* btvacuumscan --- scan the index for VACUUMing purposes
*
* This combines the functions of looking for leaf tuples that are deletable
* according to the vacuum callback, looking for empty pages that can be
* deleted, and looking for old deleted pages that can be recycled. Both
* btbulkdelete and btvacuumcleanup invoke this (the latter only if no
* btbulkdelete call occurred).
*
* The caller is responsible for initially allocating/zeroing a stats struct
* and for obtaining a vacuum cycle ID if necessary.
*/
static void
btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback, void *callback_state,
BTCycleId cycleid)
{
Relation rel = info->index;
BTVacState vstate;
BlockNumber num_pages;
BlockNumber blkno;
bool needLock;
/*
* Reset counts that will be incremented during the scan; needed in case
* of multiple scans during a single VACUUM command
*/
stats->estimated_count = false;
stats->num_index_tuples = 0;
stats->pages_deleted = 0;
/* Set up info to pass down to btvacuumpage */
vstate.info = info;
vstate.stats = stats;
vstate.callback = callback;
vstate.callback_state = callback_state;
vstate.cycleid = cycleid;
vstate.lastBlockVacuumed = BTREE_METAPAGE; /* Initialise at first block */
vstate.lastBlockLocked = BTREE_METAPAGE;
vstate.totFreePages = 0;
/* Create a temporary memory context to run _bt_pagedel in */
vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
"_bt_pagedel",
ALLOCSET_DEFAULT_SIZES);
/*
* The outer loop iterates over all index pages except the metapage, in
* physical order (we hope the kernel will cooperate in providing
* read-ahead for speed). It is critical that we visit all leaf pages,
* including ones added after we start the scan, else we might fail to
* delete some deletable tuples. Hence, we must repeatedly check the
* relation length. We must acquire the relation-extension lock while
* doing so to avoid a race condition: if someone else is extending the
* relation, there is a window where bufmgr/smgr have created a new
* all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
* we manage to scan such a page here, we'll improperly assume it can be
* recycled. Taking the lock synchronizes things enough to prevent a
* problem: either num_pages won't include the new page, or _bt_getbuf
* already has write lock on the buffer and it will be fully initialized
* before we can examine it. (See also vacuumlazy.c, which has the same
* issue.) Also, we need not worry if a page is added immediately after
* we look; the page splitting code already has write-lock on the left
* page before it adds a right page, so we must already have processed any
* tuples due to be moved into such a page.
*
* We can skip locking for new or temp relations, however, since no one
* else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
blkno = BTREE_METAPAGE + 1;
for (;;)
{
/* Get the current relation length */
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
num_pages = RelationGetNumberOfBlocks(rel);
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Quit if we've scanned the whole relation */
if (blkno >= num_pages)
break;
/* Iterate over pages, then loop back to recheck length */
for (; blkno < num_pages; blkno++)
{
btvacuumpage(&vstate, blkno, blkno);
}
}
/*
* Check to see if we need to issue one final WAL record for this index,
* which may be needed for correctness on a hot standby node when non-MVCC
* index scans could take place.
*
* If the WAL is replayed in hot standby, the replay process needs to get
* cleanup locks on all index leaf pages, just as we've been doing here.
* However, we won't issue any WAL records about pages that have no items
* to be deleted. For pages between pages we've vacuumed, the replay code
* will take locks under the direction of the lastBlockVacuumed fields in
* the XLOG_BTREE_VACUUM WAL records. To cover pages after the last one
* we vacuum, we need to issue a dummy XLOG_BTREE_VACUUM WAL record
* against the last leaf page in the index, if that one wasn't vacuumed.
*/
if (XLogStandbyInfoActive() &&
vstate.lastBlockVacuumed < vstate.lastBlockLocked)
{
Buffer buf;
/*
* The page should be valid, but we can't use _bt_getbuf() because we
* want to use a nondefault buffer access strategy. Since we aren't
* going to delete any items, getting cleanup lock again is probably
* overkill, but for consistency do that anyway.
*/
buf = ReadBufferExtended(rel, MAIN_FORKNUM, vstate.lastBlockLocked,
RBM_NORMAL, info->strategy);
LockBufferForCleanup(buf);
_bt_checkpage(rel, buf);
_bt_delitems_vacuum(rel, buf, NULL, 0, vstate.lastBlockVacuumed);
_bt_relbuf(rel, buf);
}
MemoryContextDelete(vstate.pagedelcontext);
/* update statistics */
stats->num_pages = num_pages;
stats->pages_free = vstate.totFreePages;
}
Datum
spgstat(PG_FUNCTION_ARGS)
{
text *name=PG_GETARG_TEXT_P(0);
char *relname=text_to_cstring(name);
RangeVar *relvar;
Relation index;
List *relname_list;
Oid relOid;
BlockNumber blkno = SPGIST_HEAD_BLKNO;
BlockNumber totalPages = 0,
innerPages = 0,
emptyPages = 0;
double usedSpace = 0.0;
char res[1024];
int bufferSize = -1;
int64 innerTuples = 0,
leafTuples = 0;
relname_list = stringToQualifiedNameList(relname);
relvar = makeRangeVarFromNameList(relname_list);
relOid = RangeVarGetRelid(relvar, false);
index = index_open(relOid, AccessExclusiveLock);
if ( index->rd_am == NULL )
elog(ERROR, "Relation %s.%s is not an index",
get_namespace_name(RelationGetNamespace(index)),
RelationGetRelationName(index) );
totalPages = RelationGetNumberOfBlocks(index);
for(blkno=SPGIST_HEAD_BLKNO; blkno<totalPages; blkno++)
{
Buffer buffer;
Page page;
buffer = ReadBuffer(index, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
if (SpGistPageIsLeaf(page))
{
leafTuples += SpGistPageGetMaxOffset(page);
}
else
{
innerPages++;
innerTuples += SpGistPageGetMaxOffset(page);
}
if (bufferSize < 0)
bufferSize = BufferGetPageSize(buffer) - MAXALIGN(sizeof(SpGistPageOpaqueData)) -
SizeOfPageHeaderData;
usedSpace += bufferSize - (PageGetFreeSpace(page) + sizeof(ItemIdData));
if (PageGetFreeSpace(page) + sizeof(ItemIdData) == bufferSize)
emptyPages++;
UnlockReleaseBuffer(buffer);
}
index_close(index, AccessExclusiveLock);
totalPages--; /* metapage */
snprintf(res, sizeof(res),
"totalPages: %u\n"
"innerPages: %u\n"
"leafPages: %u\n"
"emptyPages: %u\n"
"usedSpace: %.2f kbytes\n"
"freeSpace: %.2f kbytes\n"
"fillRatio: %.2f%c\n"
"leafTuples: %lld\n"
"innerTuples: %lld",
totalPages, innerPages, totalPages - innerPages, emptyPages,
usedSpace / 1024.0,
(( (double) bufferSize ) * ( (double) totalPages ) - usedSpace) / 1024,
100.0 * ( usedSpace / (( (double) bufferSize ) * ( (double) totalPages )) ),
'%',
leafTuples, innerTuples
);
PG_RETURN_TEXT_P(CStringGetTextDatum(res));
}
/*
* lazy_scan_heap() -- scan an open heap relation
*
* This routine sets commit status bits, builds lists of dead tuples
* and pages with free space, and calculates statistics on the number
* of live tuples in the heap. When done, or when we run low on space
* for dead-tuple TIDs, invoke vacuuming of indexes and heap.
*
* If there are no indexes then we just vacuum each dirty page as we
* process it, since there's no point in gathering many tuples.
*/
static void
lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats,
Relation *Irel, int nindexes, bool scan_all)
{
BlockNumber nblocks,
blkno;
HeapTupleData tuple;
char *relname;
BlockNumber empty_pages,
vacuumed_pages;
double num_tuples,
tups_vacuumed,
nkeep,
nunused;
IndexBulkDeleteResult **indstats;
int i;
PGRUsage ru0;
Buffer vmbuffer = InvalidBuffer;
BlockNumber next_not_all_visible_block;
bool skipping_all_visible_blocks;
pg_rusage_init(&ru0);
relname = RelationGetRelationName(onerel);
ereport(elevel,
(errmsg("vacuuming \"%s.%s\"",
get_namespace_name(RelationGetNamespace(onerel)),
relname)));
empty_pages = vacuumed_pages = 0;
num_tuples = tups_vacuumed = nkeep = nunused = 0;
indstats = (IndexBulkDeleteResult **)
palloc0(nindexes * sizeof(IndexBulkDeleteResult *));
nblocks = RelationGetNumberOfBlocks(onerel);
vacrelstats->rel_pages = nblocks;
vacrelstats->scanned_pages = 0;
vacrelstats->nonempty_pages = 0;
vacrelstats->latestRemovedXid = InvalidTransactionId;
lazy_space_alloc(vacrelstats, nblocks);
/*
* We want to skip pages that don't require vacuuming according to the
* visibility map, but only when we can skip at least SKIP_PAGES_THRESHOLD
* consecutive pages. Since we're reading sequentially, the OS should be
* doing readahead for us, so there's no gain in skipping a page now and
* then; that's likely to disable readahead and so be counterproductive.
* Also, skipping even a single page means that we can't update
* relfrozenxid, so we only want to do it if we can skip a goodly number
* of pages.
*
* Before entering the main loop, establish the invariant that
* next_not_all_visible_block is the next block number >= blkno that's not
* all-visible according to the visibility map, or nblocks if there's no
* such block. Also, we set up the skipping_all_visible_blocks flag,
* which is needed because we need hysteresis in the decision: once we've
* started skipping blocks, we may as well skip everything up to the next
* not-all-visible block.
*
* Note: if scan_all is true, we won't actually skip any pages; but we
* maintain next_not_all_visible_block anyway, so as to set up the
* all_visible_according_to_vm flag correctly for each page.
*/
for (next_not_all_visible_block = 0;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block, &vmbuffer))
break;
vacuum_delay_point();
}
if (next_not_all_visible_block >= SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
bool tupgone,
hastup;
int prev_dead_count;
OffsetNumber frozen[MaxOffsetNumber];
int nfrozen;
Size freespace;
bool all_visible_according_to_vm;
bool all_visible;
bool has_dead_tuples;
if (blkno == next_not_all_visible_block)
{
/* Time to advance next_not_all_visible_block */
for (next_not_all_visible_block++;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block,
&vmbuffer))
break;
vacuum_delay_point();
}
/*
* We know we can't skip the current block. But set up
* skipping_all_visible_blocks to do the right thing at the
* following blocks.
*/
if (next_not_all_visible_block - blkno > SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
all_visible_according_to_vm = false;
}
else
{
/* Current block is all-visible */
if (skipping_all_visible_blocks && !scan_all)
continue;
all_visible_according_to_vm = true;
}
vacuum_delay_point();
vacrelstats->scanned_pages++;
/*
* If we are close to overrunning the available space for dead-tuple
* TIDs, pause and do a cycle of vacuuming before we tackle this page.
*/
if ((vacrelstats->max_dead_tuples - vacrelstats->num_dead_tuples) < MaxHeapTuplesPerPage &&
vacrelstats->num_dead_tuples > 0)
{
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacrelstats->num_index_scans++;
}
buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
RBM_NORMAL, vac_strategy);
/* We need buffer cleanup lock so that we can prune HOT chains. */
LockBufferForCleanup(buf);
page = BufferGetPage(buf);
if (PageIsNew(page))
{
/*
* An all-zeroes page could be left over if a backend extends the
* relation but crashes before initializing the page. Reclaim such
* pages for use.
*
* We have to be careful here because we could be looking at a
* page that someone has just added to the relation and not yet
* been able to initialize (see RelationGetBufferForTuple). To
* protect against that, release the buffer lock, grab the
* relation extension lock momentarily, and re-lock the buffer. If
* the page is still uninitialized by then, it must be left over
* from a crashed backend, and we can initialize it.
*
* We don't really need the relation lock when this is a new or
* temp relation, but it's probably not worth the code space to
* check that, since this surely isn't a critical path.
*
* Note: the comparable code in vacuum.c need not worry because
* it's got exclusive lock on the whole relation.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockRelationForExtension(onerel, ExclusiveLock);
UnlockRelationForExtension(onerel, ExclusiveLock);
LockBufferForCleanup(buf);
if (PageIsNew(page))
{
ereport(WARNING,
(errmsg("relation \"%s\" page %u is uninitialized --- fixing",
relname, blkno)));
PageInit(page, BufferGetPageSize(buf), 0);
empty_pages++;
}
freespace = PageGetHeapFreeSpace(page);
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
if (PageIsEmpty(page))
{
empty_pages++;
freespace = PageGetHeapFreeSpace(page);
if (!PageIsAllVisible(page))
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
/*
* Prune all HOT-update chains in this page.
*
* We count tuples removed by the pruning step as removed by VACUUM.
*/
tups_vacuumed += heap_page_prune(onerel, buf, OldestXmin, false,
&vacrelstats->latestRemovedXid);
/*
* Now scan the page to collect vacuumable items and check for tuples
* requiring freezing.
*/
all_visible = true;
has_dead_tuples = false;
nfrozen = 0;
hastup = false;
prev_dead_count = vacrelstats->num_dead_tuples;
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused items require no processing, but we count 'em */
if (!ItemIdIsUsed(itemid))
{
nunused += 1;
continue;
}
/* Redirect items mustn't be touched */
if (ItemIdIsRedirected(itemid))
{
hastup = true; /* this page won't be truncatable */
continue;
}
ItemPointerSet(&(tuple.t_self), blkno, offnum);
/*
* DEAD item pointers are to be vacuumed normally; but we don't
* count them in tups_vacuumed, else we'd be double-counting (at
* least in the common case where heap_page_prune() just freed up
* a non-HOT tuple).
*/
if (ItemIdIsDead(itemid))
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
all_visible = false;
continue;
}
Assert(ItemIdIsNormal(itemid));
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tupgone = false;
switch (HeapTupleSatisfiesVacuum(tuple.t_data, OldestXmin, buf))
{
case HEAPTUPLE_DEAD:
/*
* Ordinarily, DEAD tuples would have been removed by
* heap_page_prune(), but it's possible that the tuple
* state changed since heap_page_prune() looked. In
* particular an INSERT_IN_PROGRESS tuple could have
* changed to DEAD if the inserter aborted. So this
* cannot be considered an error condition.
*
* If the tuple is HOT-updated then it must only be
* removed by a prune operation; so we keep it just as if
* it were RECENTLY_DEAD. Also, if it's a heap-only
* tuple, we choose to keep it, because it'll be a lot
* cheaper to get rid of it in the next pruning pass than
* to treat it like an indexed tuple.
*/
if (HeapTupleIsHotUpdated(&tuple) ||
HeapTupleIsHeapOnly(&tuple))
nkeep += 1;
else
tupgone = true; /* we can delete the tuple */
all_visible = false;
break;
case HEAPTUPLE_LIVE:
/* Tuple is good --- but let's do some validity checks */
if (onerel->rd_rel->relhasoids &&
!OidIsValid(HeapTupleGetOid(&tuple)))
elog(WARNING, "relation \"%s\" TID %u/%u: OID is invalid",
relname, blkno, offnum);
/*
* Is the tuple definitely visible to all transactions?
*
* NB: Like with per-tuple hint bits, we can't set the
* PD_ALL_VISIBLE flag if the inserter committed
* asynchronously. See SetHintBits for more info. Check
* that the HEAP_XMIN_COMMITTED hint bit is set because of
* that.
*/
if (all_visible)
{
TransactionId xmin;
if (!(tuple.t_data->t_infomask & HEAP_XMIN_COMMITTED))
{
all_visible = false;
break;
}
/*
* The inserter definitely committed. But is it old
* enough that everyone sees it as committed?
*/
xmin = HeapTupleHeaderGetXmin(tuple.t_data);
if (!TransactionIdPrecedes(xmin, OldestXmin))
{
all_visible = false;
break;
}
}
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must not remove it
* from relation.
*/
nkeep += 1;
all_visible = false;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (tupgone)
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
HeapTupleHeaderAdvanceLatestRemovedXid(tuple.t_data,
&vacrelstats->latestRemovedXid);
tups_vacuumed += 1;
has_dead_tuples = true;
}
else
{
num_tuples += 1;
hastup = true;
/*
* Each non-removable tuple must be checked to see if it needs
* freezing. Note we already have exclusive buffer lock.
*/
if (heap_freeze_tuple(tuple.t_data, FreezeLimit,
InvalidBuffer))
frozen[nfrozen++] = offnum;
}
} /* scan along page */
/*
* If we froze any tuples, mark the buffer dirty, and write a WAL
* record recording the changes. We must log the changes to be
* crash-safe against future truncation of CLOG.
*/
if (nfrozen > 0)
{
MarkBufferDirty(buf);
if (RelationNeedsWAL(onerel))
{
XLogRecPtr recptr;
recptr = log_heap_freeze(onerel, buf, FreezeLimit,
frozen, nfrozen);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
/*
* If there are no indexes then we can vacuum the page right now
* instead of doing a second scan.
*/
if (nindexes == 0 &&
vacrelstats->num_dead_tuples > 0)
{
/* Remove tuples from heap */
lazy_vacuum_page(onerel, blkno, buf, 0, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacuumed_pages++;
}
freespace = PageGetHeapFreeSpace(page);
/* Update the all-visible flag on the page */
if (!PageIsAllVisible(page) && all_visible)
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
/*
* It's possible for the value returned by GetOldestXmin() to move
* backwards, so it's not wrong for us to see tuples that appear to
* not be visible to everyone yet, while PD_ALL_VISIBLE is already
* set. The real safe xmin value never moves backwards, but
* GetOldestXmin() is conservative and sometimes returns a value
* that's unnecessarily small, so if we see that contradiction it just
* means that the tuples that we think are not visible to everyone yet
* actually are, and the PD_ALL_VISIBLE flag is correct.
*
* There should never be dead tuples on a page with PD_ALL_VISIBLE
* set, however.
*/
else if (PageIsAllVisible(page) && has_dead_tuples)
{
elog(WARNING, "page containing dead tuples is marked as all-visible in relation \"%s\" page %u",
relname, blkno);
PageClearAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
/*
* Normally, we would drop the lock on the heap page before
* updating the visibility map, but since this case shouldn't
* happen anyway, don't worry about that.
*/
visibilitymap_clear(onerel, blkno);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm && all_visible)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(buf);
/* Remember the location of the last page with nonremovable tuples */
if (hastup)
vacrelstats->nonempty_pages = blkno + 1;
/*
* If we remembered any tuples for deletion, then the page will be
* visited again by lazy_vacuum_heap, which will compute and record
* its post-compaction free space. If not, then we're done with this
* page, so remember its free space as-is. (This path will always be
* taken if there are no indexes.)
*/
if (vacrelstats->num_dead_tuples == prev_dead_count)
RecordPageWithFreeSpace(onerel, blkno, freespace);
}
/* save stats for use later */
vacrelstats->scanned_tuples = num_tuples;
vacrelstats->tuples_deleted = tups_vacuumed;
/* now we can compute the new value for pg_class.reltuples */
vacrelstats->new_rel_tuples = vac_estimate_reltuples(onerel, false,
nblocks,
vacrelstats->scanned_pages,
num_tuples);
/* If any tuples need to be deleted, perform final vacuum cycle */
/* XXX put a threshold on min number of tuples here? */
if (vacrelstats->num_dead_tuples > 0)
{
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
vacrelstats->num_index_scans++;
}
/* Release the pin on the visibility map page */
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
/* Do post-vacuum cleanup and statistics update for each index */
for (i = 0; i < nindexes; i++)
lazy_cleanup_index(Irel[i], indstats[i], vacrelstats);
/* If no indexes, make log report that lazy_vacuum_heap would've made */
if (vacuumed_pages)
ereport(elevel,
(errmsg("\"%s\": removed %.0f row versions in %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, vacuumed_pages)));
ereport(elevel,
(errmsg("\"%s\": found %.0f removable, %.0f nonremovable row versions in %u out of %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, num_tuples,
vacrelstats->scanned_pages, nblocks),
errdetail("%.0f dead row versions cannot be removed yet.\n"
"There were %.0f unused item pointers.\n"
"%u pages are entirely empty.\n"
"%s.",
nkeep,
nunused,
empty_pages,
pg_rusage_show(&ru0))));
}
/*
* get_relation_info -
* Retrieves catalog information for a given relation.
*
* Given the Oid of the relation, return the following info into fields
* of the RelOptInfo struct:
*
* min_attr lowest valid AttrNumber
* max_attr highest valid AttrNumber
* indexlist list of IndexOptInfos for relation's indexes
* pages number of pages
* tuples number of tuples
*
* Also, initialize the attr_needed[] and attr_widths[] arrays. In most
* cases these are left as zeroes, but sometimes we need to compute attr
* widths here, and we may as well cache the results for costsize.c.
*
* If inhparent is true, all we need to do is set up the attr arrays:
* the RelOptInfo actually represents the appendrel formed by an inheritance
* tree, and so the parent rel's physical size and index information isn't
* important for it.
*/
void
get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
RelOptInfo *rel)
{
Index varno = rel->relid;
Relation relation;
bool hasindex;
List *indexinfos = NIL;
/*
* We need not lock the relation since it was already locked, either by
* the rewriter or when expand_inherited_rtentry() added it to the query's
* rangetable.
*/
relation = heap_open(relationObjectId, NoLock);
/* Temporary and unlogged relations are inaccessible during recovery. */
if (!RelationNeedsWAL(relation) && RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary or unlogged relations during recovery")));
rel->min_attr = FirstLowInvalidHeapAttributeNumber + 1;
rel->max_attr = RelationGetNumberOfAttributes(relation);
rel->reltablespace = RelationGetForm(relation)->reltablespace;
Assert(rel->max_attr >= rel->min_attr);
rel->attr_needed = (Relids *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(Relids));
rel->attr_widths = (int32 *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(int32));
/*
* Estimate relation size --- unless it's an inheritance parent, in which
* case the size will be computed later in set_append_rel_pathlist, and we
* must leave it zero for now to avoid bollixing the total_table_pages
* calculation.
*/
if (!inhparent)
estimate_rel_size(relation, rel->attr_widths - rel->min_attr,
&rel->pages, &rel->tuples, &rel->allvisfrac);
/*
* Make list of indexes. Ignore indexes on system catalogs if told to.
* Don't bother with indexes for an inheritance parent, either.
*/
if (inhparent ||
(IgnoreSystemIndexes && IsSystemClass(relation->rd_rel)))
hasindex = false;
else
hasindex = relation->rd_rel->relhasindex;
if (hasindex)
{
List *indexoidlist;
ListCell *l;
LOCKMODE lmode;
indexoidlist = RelationGetIndexList(relation);
/*
* For each index, we get the same type of lock that the executor will
* need, and do not release it. This saves a couple of trips to the
* shared lock manager while not creating any real loss of
* concurrency, because no schema changes could be happening on the
* index while we hold lock on the parent rel, and neither lock type
* blocks any other kind of index operation.
*/
if (rel->relid == root->parse->resultRelation)
lmode = RowExclusiveLock;
else
lmode = AccessShareLock;
foreach(l, indexoidlist)
{
Oid indexoid = lfirst_oid(l);
Relation indexRelation;
Form_pg_index index;
IndexOptInfo *info;
int ncolumns;
int i;
/*
* Extract info from the relation descriptor for the index.
*/
indexRelation = index_open(indexoid, lmode);
index = indexRelation->rd_index;
/*
* Ignore invalid indexes, since they can't safely be used for
* queries. Note that this is OK because the data structure we
* are constructing is only used by the planner --- the executor
* still needs to insert into "invalid" indexes!
*/
if (!index->indisvalid)
{
index_close(indexRelation, NoLock);
continue;
}
/*
* If the index is valid, but cannot yet be used, ignore it; but
* mark the plan we are generating as transient. See
* src/backend/access/heap/README.HOT for discussion.
*/
if (index->indcheckxmin &&
!TransactionIdPrecedes(HeapTupleHeaderGetXmin(indexRelation->rd_indextuple->t_data),
TransactionXmin))
{
root->glob->transientPlan = true;
index_close(indexRelation, NoLock);
continue;
}
info = makeNode(IndexOptInfo);
info->indexoid = index->indexrelid;
info->reltablespace =
RelationGetForm(indexRelation)->reltablespace;
info->rel = rel;
info->ncolumns = ncolumns = index->indnatts;
info->indexkeys = (int *) palloc(sizeof(int) * ncolumns);
info->indexcollations = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->opfamily = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->opcintype = (Oid *) palloc(sizeof(Oid) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
info->indexkeys[i] = index->indkey.values[i];
info->indexcollations[i] = indexRelation->rd_indcollation[i];
info->opfamily[i] = indexRelation->rd_opfamily[i];
info->opcintype[i] = indexRelation->rd_opcintype[i];
}
info->relam = indexRelation->rd_rel->relam;
info->amcostestimate = indexRelation->rd_am->amcostestimate;
info->canreturn = index_can_return(indexRelation);
info->amcanorderbyop = indexRelation->rd_am->amcanorderbyop;
info->amoptionalkey = indexRelation->rd_am->amoptionalkey;
info->amsearcharray = indexRelation->rd_am->amsearcharray;
info->amsearchnulls = indexRelation->rd_am->amsearchnulls;
info->amhasgettuple = OidIsValid(indexRelation->rd_am->amgettuple);
info->amhasgetbitmap = OidIsValid(indexRelation->rd_am->amgetbitmap);
/*
* Fetch the ordering information for the index, if any.
*/
if (info->relam == BTREE_AM_OID)
{
/*
* If it's a btree index, we can use its opfamily OIDs
* directly as the sort ordering opfamily OIDs.
*/
Assert(indexRelation->rd_am->amcanorder);
info->sortopfamily = info->opfamily;
info->reverse_sort = (bool *) palloc(sizeof(bool) * ncolumns);
info->nulls_first = (bool *) palloc(sizeof(bool) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
int16 opt = indexRelation->rd_indoption[i];
info->reverse_sort[i] = (opt & INDOPTION_DESC) != 0;
info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
}
}
else if (indexRelation->rd_am->amcanorder)
{
/*
* Otherwise, identify the corresponding btree opfamilies by
* trying to map this index's "<" operators into btree. Since
* "<" uniquely defines the behavior of a sort order, this is
* a sufficient test.
*
* XXX This method is rather slow and also requires the
* undesirable assumption that the other index AM numbers its
* strategies the same as btree. It'd be better to have a way
* to explicitly declare the corresponding btree opfamily for
* each opfamily of the other index type. But given the lack
* of current or foreseeable amcanorder index types, it's not
* worth expending more effort on now.
*/
info->sortopfamily = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->reverse_sort = (bool *) palloc(sizeof(bool) * ncolumns);
info->nulls_first = (bool *) palloc(sizeof(bool) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
int16 opt = indexRelation->rd_indoption[i];
Oid ltopr;
Oid btopfamily;
Oid btopcintype;
int16 btstrategy;
info->reverse_sort[i] = (opt & INDOPTION_DESC) != 0;
info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
ltopr = get_opfamily_member(info->opfamily[i],
info->opcintype[i],
info->opcintype[i],
BTLessStrategyNumber);
if (OidIsValid(ltopr) &&
get_ordering_op_properties(ltopr,
&btopfamily,
&btopcintype,
&btstrategy) &&
btopcintype == info->opcintype[i] &&
btstrategy == BTLessStrategyNumber)
{
/* Successful mapping */
info->sortopfamily[i] = btopfamily;
}
else
{
/* Fail ... quietly treat index as unordered */
info->sortopfamily = NULL;
info->reverse_sort = NULL;
info->nulls_first = NULL;
break;
}
}
}
else
{
info->sortopfamily = NULL;
info->reverse_sort = NULL;
info->nulls_first = NULL;
}
/*
* Fetch the index expressions and predicate, if any. We must
* modify the copies we obtain from the relcache to have the
* correct varno for the parent relation, so that they match up
* correctly against qual clauses.
*/
info->indexprs = RelationGetIndexExpressions(indexRelation);
info->indpred = RelationGetIndexPredicate(indexRelation);
if (info->indexprs && varno != 1)
ChangeVarNodes((Node *) info->indexprs, 1, varno, 0);
if (info->indpred && varno != 1)
ChangeVarNodes((Node *) info->indpred, 1, varno, 0);
/* Build targetlist using the completed indexprs data */
info->indextlist = build_index_tlist(root, info, relation);
info->predOK = false; /* set later in indxpath.c */
info->unique = index->indisunique;
info->immediate = index->indimmediate;
info->hypothetical = false;
/*
* Estimate the index size. If it's not a partial index, we lock
* the number-of-tuples estimate to equal the parent table; if it
* is partial then we have to use the same methods as we would for
* a table, except we can be sure that the index is not larger
* than the table.
*/
if (info->indpred == NIL)
{
info->pages = RelationGetNumberOfBlocks(indexRelation);
info->tuples = rel->tuples;
}
else
{
double allvisfrac; /* dummy */
estimate_rel_size(indexRelation, NULL,
&info->pages, &info->tuples, &allvisfrac);
if (info->tuples > rel->tuples)
info->tuples = rel->tuples;
}
index_close(indexRelation, NoLock);
indexinfos = lcons(info, indexinfos);
}
list_free(indexoidlist);
}
