/*
* Verify that a freshly-read page looks sane.
*/
void
gistcheckpage(Relation rel, Buffer buf)
{
Page page = BufferGetPage(buf);
/*
* ReadBuffer verifies that every newly-read page passes
* PageHeaderIsValid, which means it either contains a reasonably sane
* page header or is all-zero. We have to defend against the all-zero
* case, however.
*/
if (PageIsNew(page))
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" contains unexpected zero page at block %u",
RelationGetRelationName(rel),
BufferGetBlockNumber(buf)),
errhint("Please REINDEX it.")));
/*
* Additionally check that the special area looks sane.
*/
if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GISTPageOpaqueData)))
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" contains corrupted page at block %u",
RelationGetRelationName(rel),
BufferGetBlockNumber(buf)),
errhint("Please REINDEX it.")));
}
/*
* PageGetTempPageCopySpecial
* Get a temporary page in local memory for special processing.
* The page is PageInit'd with the same special-space size as the
* given page, and the special space is copied from the given page.
*/
Page
PageGetTempPageCopySpecial(Page page)
{
Size pageSize;
Page temp;
pageSize = PageGetPageSize(page);
temp = (Page) palloc(pageSize);
PageInit(temp, pageSize, PageGetSpecialSize(page));
memcpy(PageGetSpecialPointer(temp),
PageGetSpecialPointer(page),
PageGetSpecialSize(page));
return temp;
}
/*
* pgstat_hash_page -- check tuples in a hash page
*/
static void
pgstat_hash_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno,
BufferAccessStrategy bstrategy)
{
Buffer buf;
Page page;
_hash_getlock(rel, blkno, HASH_SHARE);
buf = _hash_getbuf_with_strategy(rel, blkno, HASH_READ, 0, bstrategy);
page = BufferGetPage(buf);
if (PageGetSpecialSize(page) == MAXALIGN(sizeof(HashPageOpaqueData)))
{
HashPageOpaque opaque;
opaque = (HashPageOpaque) PageGetSpecialPointer(page);
switch (opaque->hasho_flag)
{
case LH_UNUSED_PAGE:
stat->free_space += BLCKSZ;
break;
case LH_BUCKET_PAGE:
case LH_OVERFLOW_PAGE:
pgstat_index_page(stat, page, FirstOffsetNumber,
PageGetMaxOffsetNumber(page));
break;
case LH_BITMAP_PAGE:
case LH_META_PAGE:
default:
break;
}
}
else
{
/* maybe corrupted */
}
_hash_relbuf(rel, buf);
_hash_droplock(rel, blkno, HASH_SHARE);
}
/*
* _hash_checkpage -- sanity checks on the format of all hash pages
*
* If flags is not zero, it is a bitwise OR of the acceptable values of
* hasho_flag.
*/
void
_hash_checkpage(Relation rel, Buffer buf, int flags)
{
Page page = BufferGetPage(buf);
/*
* ReadBuffer verifies that every newly-read page passes
* PageHeaderIsValid, which means it either contains a reasonably sane
* page header or is all-zero. We have to defend against the all-zero
* case, however.
*/
if (PageIsNew(page))
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" contains unexpected zero page at block %u",
RelationGetRelationName(rel),
BufferGetBlockNumber(buf)),
errhint("Please REINDEX it.")));
/*
* Additionally check that the special area looks sane.
*/
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)),
errhint("Please REINDEX it.")));
if (flags)
{
HashPageOpaque opaque = (HashPageOpaque) PageGetSpecialPointer(page);
if ((opaque->hasho_flag & flags) == 0)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" contains corrupted page at block %u",
RelationGetRelationName(rel),
BufferGetBlockNumber(buf)),
errhint("Please REINDEX it.")));
}
/*
* When checking the metapage, also verify magic number and version.
*/
if (flags == LH_META_PAGE)
{
HashMetaPage metap = HashPageGetMeta(page);
if (metap->hashm_magic != HASH_MAGIC)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" is not a hash index",
RelationGetRelationName(rel))));
if (metap->hashm_version != HASH_VERSION)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" has wrong hash version",
RelationGetRelationName(rel)),
errhint("Please REINDEX it.")));
}
}
/* ------------------------------------------------------
* 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));
}
/*
* Verify that the given bytea contains a HASH page, or die in the attempt.
* A pointer to a palloc'd, properly aligned copy of the page is returned.
*/
static Page
verify_hash_page(bytea *raw_page, int flags)
{
Page page = get_page_from_raw(raw_page);
int pagetype = LH_UNUSED_PAGE;
/* Treat new pages as unused. */
if (!PageIsNew(page))
{
HashPageOpaque pageopaque;
if (PageGetSpecialSize(page) != MAXALIGN(sizeof(HashPageOpaqueData)))
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index table contains corrupted page")));
pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
if (pageopaque->hasho_page_id != HASHO_PAGE_ID)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("page is not a hash page"),
errdetail("Expected %08x, got %08x.",
HASHO_PAGE_ID, pageopaque->hasho_page_id)));
pagetype = pageopaque->hasho_flag & LH_PAGE_TYPE;
}
/* Check that page type is sane. */
if (pagetype != LH_OVERFLOW_PAGE && pagetype != LH_BUCKET_PAGE &&
pagetype != LH_BITMAP_PAGE && pagetype != LH_META_PAGE &&
pagetype != LH_UNUSED_PAGE)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid hash page type %08x", pagetype)));
/* If requested, verify page type. */
if (flags != 0 && (pagetype & flags) == 0)
{
switch (flags)
{
case LH_META_PAGE:
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("page is not a hash meta page")));
case LH_BUCKET_PAGE | LH_OVERFLOW_PAGE:
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("page is not a hash bucket or overflow page")));
case LH_OVERFLOW_PAGE:
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("page is not a hash overflow page")));
default:
elog(ERROR,
"hash page of type %08x not in mask %08x",
pagetype, flags);
}
}
/*
* If it is the metapage, also verify magic number and version.
*/
if (pagetype == LH_META_PAGE)
{
HashMetaPage metap = HashPageGetMeta(page);
if (metap->hashm_magic != HASH_MAGIC)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("invalid magic number for metadata"),
errdetail("Expected 0x%08x, got 0x%08x.",
HASH_MAGIC, metap->hashm_magic)));
if (metap->hashm_version != HASH_VERSION)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("invalid version for metadata"),
errdetail("Expected %d, got %d",
HASH_VERSION, metap->hashm_version)));
}
return page;
}
Datum
gin_leafpage_items(PG_FUNCTION_ARGS)
{
bytea *raw_page = PG_GETARG_BYTEA_P(0);
int raw_page_size;
FuncCallContext *fctx;
gin_leafpage_items_state *inter_call_data;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use raw page functions"))));
raw_page_size = VARSIZE(raw_page) - VARHDRSZ;
if (SRF_IS_FIRSTCALL())
{
TupleDesc tupdesc;
MemoryContext mctx;
Page page;
GinPageOpaque opaq;
if (raw_page_size < BLCKSZ)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page too small (%d bytes)", raw_page_size)));
page = VARDATA(raw_page);
if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData)))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page is not a valid GIN data leaf page"),
errdetail("Special size %d, expected %d",
(int) PageGetSpecialSize(page),
(int) MAXALIGN(sizeof(GinPageOpaqueData)))));
opaq = (GinPageOpaque) PageGetSpecialPointer(page);
if (opaq->flags != (GIN_DATA | GIN_LEAF | GIN_COMPRESSED))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page is not a compressed GIN data leaf page"),
errdetail("Flags %04X, expected %04X",
opaq->flags,
(GIN_DATA | GIN_LEAF | GIN_COMPRESSED))));
fctx = SRF_FIRSTCALL_INIT();
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
inter_call_data = palloc(sizeof(gin_leafpage_items_state));
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
inter_call_data->tupd = tupdesc;
inter_call_data->seg = GinDataLeafPageGetPostingList(page);
inter_call_data->lastseg = (GinPostingList *)
(((char *) inter_call_data->seg) +
GinDataLeafPageGetPostingListSize(page));
fctx->user_fctx = inter_call_data;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
inter_call_data = fctx->user_fctx;
if (inter_call_data->seg != inter_call_data->lastseg)
{
GinPostingList *cur = inter_call_data->seg;
HeapTuple resultTuple;
Datum result;
Datum values[3];
bool nulls[3];
int ndecoded,
i;
ItemPointer tids;
Datum *tids_datum;
memset(nulls, 0, sizeof(nulls));
values[0] = ItemPointerGetDatum(&cur->first);
values[1] = UInt16GetDatum(cur->nbytes);
/* build an array of decoded item pointers */
tids = ginPostingListDecode(cur, &ndecoded);
tids_datum = (Datum *) palloc(ndecoded * sizeof(Datum));
for (i = 0; i < ndecoded; i++)
tids_datum[i] = ItemPointerGetDatum(&tids[i]);
values[2] = PointerGetDatum(construct_array(tids_datum,
ndecoded,
TIDOID,
sizeof(ItemPointerData),
false, 's'));
pfree(tids_datum);
pfree(tids);
/* Build and return the result tuple. */
resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls);
result = HeapTupleGetDatum(resultTuple);
inter_call_data->seg = GinNextPostingListSegment(cur);
SRF_RETURN_NEXT(fctx, result);
}
else
SRF_RETURN_DONE(fctx);
}