/*
* _hash_getnewbuf() -- Get a new page at the end of the index.
*
* This has the same API as _hash_getinitbuf, except that we are adding
* a page to the index, and hence expect the page to be past the
* logical EOF. (However, we have to support the case where it isn't,
* since a prior try might have crashed after extending the filesystem
* EOF but before updating the metapage to reflect the added page.)
*
* It is caller's responsibility to ensure that only one process can
* extend the index at a time.
*/
Buffer
_hash_getnewbuf(Relation rel, BlockNumber blkno, ForkNumber forkNum)
{
BlockNumber nblocks = RelationGetNumberOfBlocksInFork(rel, forkNum);
Buffer buf;
if (blkno == P_NEW)
elog(ERROR, "hash AM does not use P_NEW");
if (blkno > nblocks)
elog(ERROR, "access to noncontiguous page in hash index \"%s\"",
RelationGetRelationName(rel));
/* smgr insists we use P_NEW to extend the relation */
if (blkno == nblocks)
{
buf = ReadBufferExtended(rel, forkNum, P_NEW, RBM_NORMAL, NULL);
if (BufferGetBlockNumber(buf) != blkno)
elog(ERROR, "unexpected hash relation size: %u, should be %u",
BufferGetBlockNumber(buf), blkno);
}
else
buf = ReadBufferExtended(rel, forkNum, blkno, RBM_ZERO, NULL);
LockBuffer(buf, HASH_WRITE);
/* ref count and lock type are correct */
/* initialize the page */
_hash_pageinit(BufferGetPage(buf), BufferGetPageSize(buf));
return buf;
}
/*
* _hash_initbuf() -- Get and initialize a buffer by bucket number.
*/
void
_hash_initbuf(Buffer buf, uint32 max_bucket, uint32 num_bucket, uint32 flag,
bool initpage)
{
HashPageOpaque pageopaque;
Page page;
page = BufferGetPage(buf);
/* initialize the page */
if (initpage)
_hash_pageinit(page, BufferGetPageSize(buf));
pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
/*
* Set hasho_prevblkno with current hashm_maxbucket. This value will be
* used to validate cached HashMetaPageData. See
* _hash_getbucketbuf_from_hashkey().
*/
pageopaque->hasho_prevblkno = max_bucket;
pageopaque->hasho_nextblkno = InvalidBlockNumber;
pageopaque->hasho_bucket = num_bucket;
pageopaque->hasho_flag = flag;
pageopaque->hasho_page_id = HASHO_PAGE_ID;
}
/*
* _hash_initbitmapbuffer()
*
* Initialize a new bitmap page. All bits in the new bitmap page are set to
* "1", indicating "in use".
*/
void
_hash_initbitmapbuffer(Buffer buf, uint16 bmsize, bool initpage)
{
Page pg;
HashPageOpaque op;
uint32 *freep;
pg = BufferGetPage(buf);
/* initialize the page */
if (initpage)
_hash_pageinit(pg, BufferGetPageSize(buf));
/* initialize the page's special space */
op = (HashPageOpaque) PageGetSpecialPointer(pg);
op->hasho_prevblkno = InvalidBlockNumber;
op->hasho_nextblkno = InvalidBlockNumber;
op->hasho_bucket = -1;
op->hasho_flag = LH_BITMAP_PAGE;
op->hasho_page_id = HASHO_PAGE_ID;
/* set all of the bits to 1 */
freep = HashPageGetBitmap(pg);
MemSet(freep, 0xFF, bmsize);
/*
* Set pd_lower just past the end of the bitmap page data. We could even
* set pd_lower equal to pd_upper, but this is more precise and makes the
* page look compressible to xlog.c.
*/
((PageHeader) pg)->pd_lower = ((char *) freep + bmsize) - (char *) pg;
}
/*
* _bitmap_init_lovpage -- initialize a new LOV page.
*/
void
_bitmap_init_lovpage(Relation rel __attribute__((unused)), Buffer buf)
{
Page page;
page = (Page) BufferGetPage(buf);
if(PageIsNew(page))
PageInit(page, BufferGetPageSize(buf), 0);
}
void
SpGistInitMetabuffer(Buffer b, Relation index)
{
SpGistMetaPageData *metadata;
Page page = BufferGetPage(b);
SpGistInitPage(page, SPGIST_META, BufferGetPageSize(b));
metadata = SpGistPageGetMeta(page);
memset(metadata, 0, sizeof(SpGistMetaPageData));
metadata->magickNumber = SPGIST_MAGICK_NUMBER;
}
/*
* _hash_addovflpage
*
* Add an overflow page to the bucket whose last page is pointed to by 'buf'.
*
* On entry, the caller must hold a pin but no lock on 'buf'. The pin is
* dropped before exiting (we assume the caller is not interested in 'buf'
* anymore). The returned overflow page will be pinned and write-locked;
* it is guaranteed to be empty.
*
* The caller must hold a pin, but no lock, on the metapage buffer.
* That buffer is returned in the same state.
*
* The caller must hold at least share lock on the bucket, to ensure that
* no one else tries to compact the bucket meanwhile. This guarantees that
* 'buf' won't stop being part of the bucket while it's unlocked.
*
* NB: since this could be executed concurrently by multiple processes,
* one should not assume that the returned overflow page will be the
* immediate successor of the originally passed 'buf'. Additional overflow
* pages might have been added to the bucket chain in between.
*/
Buffer
_hash_addovflpage(Relation rel, Buffer metabuf, Buffer buf)
{
Buffer ovflbuf;
Page page;
Page ovflpage;
HashPageOpaque pageopaque;
HashPageOpaque ovflopaque;
/* allocate and lock an empty overflow page */
ovflbuf = _hash_getovflpage(rel, metabuf);
ovflpage = BufferGetPage(ovflbuf);
/*
* Write-lock the tail page. It is okay to hold two buffer locks here
* since there cannot be anyone else contending for access to ovflbuf.
*/
_hash_chgbufaccess(rel, buf, HASH_NOLOCK, HASH_WRITE);
/* loop to find current tail page, in case someone else inserted too */
for (;;)
{
BlockNumber nextblkno;
_hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
page = BufferGetPage(buf);
pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
nextblkno = pageopaque->hasho_nextblkno;
if (!BlockNumberIsValid(nextblkno))
break;
/* we assume we do not need to write the unmodified page */
_hash_relbuf(rel, buf);
buf = _hash_getbuf(rel, nextblkno, HASH_WRITE);
}
/* now that we have correct backlink, initialize new overflow page */
_hash_pageinit(ovflpage, BufferGetPageSize(ovflbuf));
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
ovflopaque->hasho_prevblkno = BufferGetBlockNumber(buf);
ovflopaque->hasho_nextblkno = InvalidBlockNumber;
ovflopaque->hasho_bucket = pageopaque->hasho_bucket;
ovflopaque->hasho_flag = LH_OVERFLOW_PAGE;
ovflopaque->hasho_filler = HASHO_FILL;
MarkBufferDirty(ovflbuf);
/* logically chain overflow page to previous page */
pageopaque->hasho_nextblkno = BufferGetBlockNumber(ovflbuf);
_hash_wrtbuf(rel, buf);
return ovflbuf;
}
/*
* _hash_initbitmap()
*
* Initialize a new bitmap page. The metapage has a write-lock upon
* entering the function, and must be written by caller after return.
*
* 'blkno' is the block number of the new bitmap page.
*
* All bits in the new bitmap page are set to "1", indicating "in use".
*/
void
_hash_initbitmap(Relation rel, HashMetaPage metap, BlockNumber blkno)
{
Buffer buf;
Page pg;
HashPageOpaque op;
uint32 *freep;
/*
* It is okay to write-lock the new bitmap page while holding metapage
* write lock, because no one else could be contending for the new page.
* Also, the metapage lock makes it safe to extend the index using P_NEW,
* which we want to do to ensure the smgr's idea of the relation size
* stays in step with ours.
*
* There is some loss of concurrency in possibly doing I/O for the new
* page while holding the metapage lock, but this path is taken so seldom
* that it's not worth worrying about.
*/
buf = _hash_getbuf(rel, P_NEW, HASH_WRITE);
if (BufferGetBlockNumber(buf) != blkno)
elog(ERROR, "unexpected hash relation size: %u, should be %u",
BufferGetBlockNumber(buf), blkno);
pg = BufferGetPage(buf);
/* initialize the page */
_hash_pageinit(pg, BufferGetPageSize(buf));
op = (HashPageOpaque) PageGetSpecialPointer(pg);
op->hasho_prevblkno = InvalidBlockNumber;
op->hasho_nextblkno = InvalidBlockNumber;
op->hasho_bucket = -1;
op->hasho_flag = LH_BITMAP_PAGE;
op->hasho_filler = HASHO_FILL;
/* set all of the bits to 1 */
freep = HashPageGetBitmap(pg);
MemSet(freep, 0xFF, BMPGSZ_BYTE(metap));
/* write out the new bitmap page (releasing write lock and pin) */
_hash_wrtbuf(rel, buf);
/* add the new bitmap page to the metapage's list of bitmaps */
/* metapage already has a write lock */
if (metap->hashm_nmaps >= HASH_MAX_BITMAPS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("out of overflow pages in hash index \"%s\"",
RelationGetRelationName(rel))));
metap->hashm_mapp[metap->hashm_nmaps] = blkno;
metap->hashm_nmaps++;
}
void
BloomInitMetabuffer(Buffer b, Relation index)
{
BloomMetaPageData *metadata;
Page page = BufferGetPage(b);
BloomInitPage(page, BLOOM_META, BufferGetPageSize(b));
metadata = BloomPageGetMeta(page);
memset(metadata, 0, sizeof(BloomMetaPageData));
metadata->magickNumber = BLOOM_MAGICK_NUMBER;
metadata->opts = *makeDefaultBloomOptions((BloomOptions*)index->rd_options);
}
static void
ginRedoDeleteListPages(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
ginxlogDeleteListPages *data = (ginxlogDeleteListPages *) XLogRecGetData(record);
Buffer metabuffer;
Page metapage;
int i;
metabuffer = XLogInitBufferForRedo(record, 0);
Assert(BufferGetBlockNumber(metabuffer) == GIN_METAPAGE_BLKNO);
metapage = BufferGetPage(metabuffer);
GinInitPage(metapage, GIN_META, BufferGetPageSize(metabuffer));
memcpy(GinPageGetMeta(metapage), &data->metadata, sizeof(GinMetaPageData));
PageSetLSN(metapage, lsn);
MarkBufferDirty(metabuffer);
/*
* In normal operation, shiftList() takes exclusive lock on all the
* pages-to-be-deleted simultaneously. During replay, however, it should
* be all right to lock them one at a time. This is dependent on the fact
* that we are deleting pages from the head of the list, and that readers
* share-lock the next page before releasing the one they are on. So we
* cannot get past a reader that is on, or due to visit, any page we are
* going to delete. New incoming readers will block behind our metapage
* lock and then see a fully updated page list.
*
* No full-page images are taken of the deleted pages. Instead, they are
* re-initialized as empty, deleted pages. Their right-links don't need to
* be preserved, because no new___ readers can see the pages, as explained
* above.
*/
for (i = 0; i < data->ndeleted; i++)
{
Buffer buffer;
Page page;
buffer = XLogInitBufferForRedo(record, i + 1);
page = BufferGetPage(buffer);
GinInitBuffer(buffer, GIN_DELETED);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
UnlockReleaseBuffer(metabuffer);
}
void
GinInitMetabuffer(Buffer b)
{
GinMetaPageData *metadata;
Page page = BufferGetPage(b);
GinInitPage(page, GIN_META, BufferGetPageSize(b));
metadata = GinPageGetMeta(page);
metadata->head = metadata->tail = InvalidBlockNumber;
metadata->tailFreeSize = 0;
metadata->nPendingPages = 0;
metadata->nPendingHeapTuples = 0;
}
static void
RTInitBuffer(Buffer b, uint32 f)
{
RTreePageOpaque opaque;
Page page;
Size pageSize;
pageSize = BufferGetPageSize(b);
page = BufferGetPage(b);
PageInit(page, pageSize, sizeof(RTreePageOpaqueData));
opaque = (RTreePageOpaque) PageGetSpecialPointer(page);
opaque->flags = f;
}
/*
* Initialize a new index page
*/
void
GISTInitBuffer(Buffer b, uint32 f)
{
GISTPageOpaque opaque;
Page page;
Size pageSize;
pageSize = BufferGetPageSize(b);
page = BufferGetPage(b);
PageInit(page, pageSize, sizeof(GISTPageOpaqueData));
opaque = GistPageGetOpaque(page);
opaque->flags = f;
opaque->rightlink = InvalidBlockNumber;
/* page was already zeroed by PageInit, so this is not needed: */
/* memset(&(opaque->nsn), 0, sizeof(GistNSN)); */
}
/*
* _bitmap_init_bitmappage() -- initialize a new page to store the bitmap.
*/
void
_bitmap_init_bitmappage(Relation rel __attribute__((unused)), Buffer buf)
{
Page page;
BMBitmapOpaque opaque;
page = (Page) BufferGetPage(buf);
if(PageIsNew(page))
PageInit(page, BufferGetPageSize(buf), sizeof(BMBitmapOpaqueData));
/* even though page may not be new, reset all values */
opaque = (BMBitmapOpaque) PageGetSpecialPointer(page);
opaque->bm_hrl_words_used = 0;
opaque->bm_bitmap_next = InvalidBlockNumber;
opaque->bm_last_tid_location = 0;
}
/*
* _hash_getinitbuf() -- Get and initialize a buffer by block number.
*
* This must be used only to fetch pages that are known to be before
* the index's filesystem EOF, but are to be filled from scratch.
* _hash_pageinit() is applied automatically. Otherwise it has
* effects similar to _hash_getbuf() with access = HASH_WRITE.
*
* When this routine returns, a write lock is set on the
* requested buffer and its reference count has been incremented
* (ie, the buffer is "locked and pinned").
*
* P_NEW is disallowed because this routine can only be used
* to access pages that are known to be before the filesystem EOF.
* Extending the index should be done with _hash_getnewbuf.
*/
Buffer
_hash_getinitbuf(Relation rel, BlockNumber blkno)
{
Buffer buf;
if (blkno == P_NEW)
elog(ERROR, "hash AM does not use P_NEW");
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_ZERO_AND_LOCK,
NULL);
/* ref count and lock type are correct */
/* initialize the page */
_hash_pageinit(BufferGetPage(buf), BufferGetPageSize(buf));
return buf;
}
static void
_bt_restore_meta(XLogReaderState *record, uint8 block_id)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer metabuf;
Page metapg;
BTMetaPageData *md;
BTPageOpaque pageop;
xl_btree_metadata *xlrec;
char *ptr;
Size len;
metabuf = XLogInitBufferForRedo(record, block_id);
ptr = XLogRecGetBlockData(record, block_id, &len);
Assert(len == sizeof(xl_btree_metadata));
Assert(BufferGetBlockNumber(metabuf) == BTREE_METAPAGE);
xlrec = (xl_btree_metadata *) ptr;
metapg = BufferGetPage(metabuf);
_bt_pageinit(metapg, BufferGetPageSize(metabuf));
md = BTPageGetMeta(metapg);
md->btm_magic = BTREE_MAGIC;
md->btm_version = BTREE_VERSION;
md->btm_root = xlrec->root;
md->btm_level = xlrec->level;
md->btm_fastroot = xlrec->fastroot;
md->btm_fastlevel = xlrec->fastlevel;
pageop = (BTPageOpaque) PageGetSpecialPointer(metapg);
pageop->btpo_flags = BTP_META;
/*
* Set pd_lower just past the end of the metadata. This is not essential
* but it makes the page look compressible to xlog.c.
*/
((PageHeader) metapg)->pd_lower =
((char *) md + sizeof(BTMetaPageData)) - (char *) metapg;
PageSetLSN(metapg, lsn);
MarkBufferDirty(metabuf);
UnlockReleaseBuffer(metabuf);
}
void
GinInitMetabuffer(Buffer b)
{
GinMetaPageData *metadata;
Page page = BufferGetPage(b);
GinInitPage(page, GIN_META, BufferGetPageSize(b));
metadata = GinPageGetMeta(page);
metadata->head = metadata->tail = InvalidBlockNumber;
metadata->tailFreeSize = 0;
metadata->nPendingPages = 0;
metadata->nPendingHeapTuples = 0;
metadata->nTotalPages = 0;
metadata->nEntryPages = 0;
metadata->nDataPages = 0;
metadata->nEntries = 0;
metadata->ginVersion = GIN_CURRENT_VERSION;
}
static void
btree_xlog_newroot(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_newroot *xlrec = (xl_btree_newroot *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque pageop;
char *ptr;
Size len;
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_flags = BTP_ROOT;
pageop->btpo_prev = pageop->btpo_next = P_NONE;
pageop->btpo.level = xlrec->level;
if (xlrec->level == 0)
pageop->btpo_flags |= BTP_LEAF;
pageop->btpo_cycleid = 0;
if (xlrec->level > 0)
{
ptr = XLogRecGetBlockData(record, 0, &len);
_bt_restore_page(page, ptr, len);
/* Clear the incomplete-split flag in left child */
_bt_clear_incomplete_split(record, 1);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
_bt_restore_meta(record, 2);
}
/*
* _hash_metapinit() -- Initialize the metadata page of a hash index,
* the two buckets that we begin with and the initial
* bitmap page.
*
* We are fairly cavalier about locking here, since we know that no one else
* could be accessing this index. In particular the rule about not holding
* multiple buffer locks is ignored.
*/
void
_hash_metapinit(Relation rel)
{
HashMetaPage metap;
HashPageOpaque pageopaque;
Buffer metabuf;
Buffer buf;
Page pg;
int32 data_width;
int32 item_width;
int32 ffactor;
uint16 i;
/* safety check */
if (RelationGetNumberOfBlocks(rel) != 0)
elog(ERROR, "cannot initialize non-empty hash index \"%s\"",
RelationGetRelationName(rel));
/*
* Determine the target fill factor (tuples per bucket) for this index.
* The idea is to make the fill factor correspond to pages about 3/4ths
* full. We can compute it exactly if the index datatype is fixed-width,
* but for var-width there's some guessing involved.
*/
data_width = get_typavgwidth(RelationGetDescr(rel)->attrs[0]->atttypid,
RelationGetDescr(rel)->attrs[0]->atttypmod);
item_width = MAXALIGN(sizeof(HashItemData)) + MAXALIGN(data_width) +
sizeof(ItemIdData); /* include the line pointer */
ffactor = (BLCKSZ * 3 / 4) / item_width;
/* keep to a sane range */
if (ffactor < 10)
ffactor = 10;
metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_WRITE);
pg = BufferGetPage(metabuf);
_hash_pageinit(pg, BufferGetPageSize(metabuf));
pageopaque = (HashPageOpaque) PageGetSpecialPointer(pg);
pageopaque->hasho_prevblkno = InvalidBlockNumber;
pageopaque->hasho_nextblkno = InvalidBlockNumber;
pageopaque->hasho_bucket = -1;
pageopaque->hasho_flag = LH_META_PAGE;
pageopaque->hasho_filler = HASHO_FILL;
metap = (HashMetaPage) pg;
metap->hashm_magic = HASH_MAGIC;
metap->hashm_version = HASH_VERSION;
metap->hashm_ntuples = 0;
metap->hashm_nmaps = 0;
metap->hashm_ffactor = ffactor;
metap->hashm_bsize = BufferGetPageSize(metabuf);
/* find largest bitmap array size that will fit in page size */
for (i = _hash_log2(metap->hashm_bsize); i > 0; --i)
{
if ((1 << i) <= (metap->hashm_bsize -
(MAXALIGN(sizeof(PageHeaderData)) +
MAXALIGN(sizeof(HashPageOpaqueData)))))
break;
}
Assert(i > 0);
metap->hashm_bmsize = 1 << i;
metap->hashm_bmshift = i + BYTE_TO_BIT;
Assert((1 << BMPG_SHIFT(metap)) == (BMPG_MASK(metap) + 1));
metap->hashm_procid = index_getprocid(rel, 1, HASHPROC);
/*
* We initialize the index with two buckets, 0 and 1, occupying physical
* blocks 1 and 2. The first freespace bitmap page is in block 3.
*/
metap->hashm_maxbucket = metap->hashm_lowmask = 1; /* nbuckets - 1 */
metap->hashm_highmask = 3; /* (nbuckets << 1) - 1 */
MemSet((char *) metap->hashm_spares, 0, sizeof(metap->hashm_spares));
MemSet((char *) metap->hashm_mapp, 0, sizeof(metap->hashm_mapp));
metap->hashm_spares[1] = 1; /* the first bitmap page is only spare */
metap->hashm_ovflpoint = 1;
metap->hashm_firstfree = 0;
/*
* Initialize the first two buckets
*/
for (i = 0; i <= 1; i++)
{
buf = _hash_getbuf(rel, BUCKET_TO_BLKNO(metap, i), HASH_WRITE);
pg = BufferGetPage(buf);
_hash_pageinit(pg, BufferGetPageSize(buf));
pageopaque = (HashPageOpaque) PageGetSpecialPointer(pg);
pageopaque->hasho_prevblkno = InvalidBlockNumber;
pageopaque->hasho_nextblkno = InvalidBlockNumber;
pageopaque->hasho_bucket = i;
pageopaque->hasho_flag = LH_BUCKET_PAGE;
pageopaque->hasho_filler = HASHO_FILL;
_hash_wrtbuf(rel, buf);
}
/*
* Initialize first bitmap page. Can't do this until we
* create the first two buckets, else smgr will complain.
*/
_hash_initbitmap(rel, metap, 3);
/* all done */
_hash_wrtbuf(rel, metabuf);
}
void
SpGistInitBuffer(Buffer b, uint16 f)
{
SpGistInitPage(BufferGetPage(b), f, BufferGetPageSize(b));
}
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));
}
static void
btree_xlog_unlink_page(uint8 info, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_unlink_page *xlrec = (xl_btree_unlink_page *) XLogRecGetData(record);
BlockNumber leftsib;
BlockNumber rightsib;
Buffer buffer;
Page page;
BTPageOpaque pageop;
leftsib = xlrec->leftsib;
rightsib = xlrec->rightsib;
/*
* In normal operation, we would lock all the pages this WAL record
* touches before changing any of them. In WAL replay, it should be okay
* to lock just one page at a time, since no concurrent index updates can
* be happening, and readers should not care whether they arrive at the
* target page or not (since it's surely empty).
*/
/* Fix left-link of right sibling */
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = leftsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Fix right-link of left sibling, if any */
if (leftsib != P_NONE)
{
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_next = rightsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/* Rewrite target page as empty deleted page */
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = leftsib;
pageop->btpo_next = rightsib;
pageop->btpo.xact = xlrec->btpo_xact;
pageop->btpo_flags = BTP_DELETED;
pageop->btpo_cycleid = 0;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
/*
* If we deleted a parent of the targeted leaf page, instead of the leaf
* itself, update the leaf to point to the next remaining child in the
* branch.
*/
if (XLogRecHasBlockRef(record, 3))
{
/*
* There is no real data on the page, so we just re-create it from
* scratch using the information from the WAL record.
*/
IndexTupleData trunctuple;
buffer = XLogInitBufferForRedo(record, 3);
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
pageop->btpo_prev = xlrec->leafleftsib;
pageop->btpo_next = xlrec->leafrightsib;
pageop->btpo.level = 0;
pageop->btpo_cycleid = 0;
/* Add a dummy hikey item */
MemSet(&trunctuple, 0, sizeof(IndexTupleData));
trunctuple.t_info = sizeof(IndexTupleData);
if (xlrec->topparent != InvalidBlockNumber)
ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
else
ItemPointerSetInvalid(&trunctuple.t_tid);
if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
false, false) == InvalidOffsetNumber)
elog(ERROR, "could not add dummy high key to half-dead page");
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/* Update metapage if needed */
if (info == XLOG_BTREE_UNLINK_PAGE_META)
_bt_restore_meta(record, 4);
}
/*
* _hash_freeovflpage() -
*
* Remove this overflow page from its bucket's chain, and mark the page as
* free. On entry, ovflbuf is write-locked; it is released before exiting.
*
* Since this function is invoked in VACUUM, we provide an access strategy
* parameter that controls fetches of the bucket pages.
*
* Returns the block number of the page that followed the given page
* in the bucket, or InvalidBlockNumber if no following page.
*
* NB: caller must not hold lock on metapage, nor on either page that's
* adjacent in the bucket chain. The caller had better hold exclusive lock
* on the bucket, too.
*/
BlockNumber
_hash_freeovflpage(Relation rel, Buffer ovflbuf,
BufferAccessStrategy bstrategy)
{
HashMetaPage metap;
Buffer metabuf;
Buffer mapbuf;
BlockNumber ovflblkno;
BlockNumber prevblkno;
BlockNumber blkno;
BlockNumber nextblkno;
HashPageOpaque ovflopaque;
Page ovflpage;
Page mappage;
uint32 *freep;
uint32 ovflbitno;
int32 bitmappage,
bitmapbit;
Bucket bucket PG_USED_FOR_ASSERTS_ONLY;
/* Get information from the doomed page */
_hash_checkpage(rel, ovflbuf, LH_OVERFLOW_PAGE);
ovflblkno = BufferGetBlockNumber(ovflbuf);
ovflpage = BufferGetPage(ovflbuf);
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
nextblkno = ovflopaque->hasho_nextblkno;
prevblkno = ovflopaque->hasho_prevblkno;
bucket = ovflopaque->hasho_bucket;
/*
* Zero the page for debugging's sake; then write and release it. (Note:
* if we failed to zero the page here, we'd have problems with the Assert
* in _hash_pageinit() when the page is reused.)
*/
MemSet(ovflpage, 0, BufferGetPageSize(ovflbuf));
_hash_wrtbuf(rel, ovflbuf);
/*
* Fix up the bucket chain. this is a doubly-linked list, so we must fix
* up the bucket chain members behind and ahead of the overflow page being
* deleted. No concurrency issues since we hold exclusive lock on the
* entire bucket.
*/
if (BlockNumberIsValid(prevblkno))
{
Buffer prevbuf = _hash_getbuf_with_strategy(rel,
prevblkno,
HASH_WRITE,
LH_BUCKET_PAGE | LH_OVERFLOW_PAGE,
bstrategy);
Page prevpage = BufferGetPage(prevbuf);
HashPageOpaque prevopaque = (HashPageOpaque) PageGetSpecialPointer(prevpage);
Assert(prevopaque->hasho_bucket == bucket);
prevopaque->hasho_nextblkno = nextblkno;
_hash_wrtbuf(rel, prevbuf);
}
if (BlockNumberIsValid(nextblkno))
{
Buffer nextbuf = _hash_getbuf_with_strategy(rel,
nextblkno,
HASH_WRITE,
LH_OVERFLOW_PAGE,
bstrategy);
Page nextpage = BufferGetPage(nextbuf);
HashPageOpaque nextopaque = (HashPageOpaque) PageGetSpecialPointer(nextpage);
Assert(nextopaque->hasho_bucket == bucket);
nextopaque->hasho_prevblkno = prevblkno;
_hash_wrtbuf(rel, nextbuf);
}
/* Note: bstrategy is intentionally not used for metapage and bitmap */
/* Read the metapage so we can determine which bitmap page to use */
metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
metap = HashPageGetMeta(BufferGetPage(metabuf));
/* Identify which bit to set */
ovflbitno = blkno_to_bitno(metap, ovflblkno);
bitmappage = ovflbitno >> BMPG_SHIFT(metap);
bitmapbit = ovflbitno & BMPG_MASK(metap);
if (bitmappage >= metap->hashm_nmaps)
elog(ERROR, "invalid overflow bit number %u", ovflbitno);
blkno = metap->hashm_mapp[bitmappage];
/* Release metapage lock while we access the bitmap page */
_hash_chgbufaccess(rel, metabuf, HASH_READ, HASH_NOLOCK);
/* Clear the bitmap bit to indicate that this overflow page is free */
mapbuf = _hash_getbuf(rel, blkno, HASH_WRITE, LH_BITMAP_PAGE);
mappage = BufferGetPage(mapbuf);
freep = HashPageGetBitmap(mappage);
Assert(ISSET(freep, bitmapbit));
CLRBIT(freep, bitmapbit);
_hash_wrtbuf(rel, mapbuf);
/* Get write-lock on metapage to update firstfree */
_hash_chgbufaccess(rel, metabuf, HASH_NOLOCK, HASH_WRITE);
/* if this is now the first free page, update hashm_firstfree */
if (ovflbitno < metap->hashm_firstfree)
{
metap->hashm_firstfree = ovflbitno;
_hash_wrtbuf(rel, metabuf);
}
else
{
/* no need to change metapage */
_hash_relbuf(rel, metabuf);
}
return nextblkno;
}
static void
btree_xlog_mark_page_halfdead(uint8 info, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_mark_page_halfdead *xlrec = (xl_btree_mark_page_halfdead *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque pageop;
IndexTupleData trunctuple;
/*
* In normal operation, we would lock all the pages this WAL record
* touches before changing any of them. In WAL replay, it should be okay
* to lock just one page at a time, since no concurrent index updates can
* be happening, and readers should not care whether they arrive at the
* target page or not (since it's surely empty).
*/
/* parent page */
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
OffsetNumber poffset;
ItemId itemid;
IndexTuple itup;
OffsetNumber nextoffset;
BlockNumber rightsib;
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
poffset = xlrec->poffset;
nextoffset = OffsetNumberNext(poffset);
itemid = PageGetItemId(page, nextoffset);
itup = (IndexTuple) PageGetItem(page, itemid);
rightsib = ItemPointerGetBlockNumber(&itup->t_tid);
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
PageIndexTupleDelete(page, nextoffset);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Rewrite the leaf page as a halfdead page */
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = xlrec->leftblk;
pageop->btpo_next = xlrec->rightblk;
pageop->btpo.level = 0;
pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
pageop->btpo_cycleid = 0;
/*
* Construct a dummy hikey item that points to the next parent to be
* deleted (if any).
*/
MemSet(&trunctuple, 0, sizeof(IndexTupleData));
trunctuple.t_info = sizeof(IndexTupleData);
if (xlrec->topparent != InvalidBlockNumber)
ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
else
ItemPointerSetInvalid(&trunctuple.t_tid);
if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
false, false) == InvalidOffsetNumber)
elog(ERROR, "could not add dummy high key to half-dead page");
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
static void
btree_xlog_split(bool onleft, bool isroot, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record);
bool isleaf = (xlrec->level == 0);
Buffer lbuf;
Buffer rbuf;
Page rpage;
BTPageOpaque ropaque;
char *datapos;
Size datalen;
Item left_hikey = NULL;
Size left_hikeysz = 0;
BlockNumber leftsib;
BlockNumber rightsib;
BlockNumber rnext;
XLogRecGetBlockTag(record, 0, NULL, NULL, &leftsib);
XLogRecGetBlockTag(record, 1, NULL, NULL, &rightsib);
if (!XLogRecGetBlockTag(record, 2, NULL, NULL, &rnext))
rnext = P_NONE;
/*
* Clear the incomplete split flag on the left sibling of the child page
* this is a downlink for. (Like in btree_xlog_insert, this can be done
* before locking the other pages)
*/
if (!isleaf)
_bt_clear_incomplete_split(record, 3);
/* Reconstruct right (new) sibling page from scratch */
rbuf = XLogInitBufferForRedo(record, 1);
datapos = XLogRecGetBlockData(record, 1, &datalen);
rpage = (Page) BufferGetPage(rbuf);
_bt_pageinit(rpage, BufferGetPageSize(rbuf));
ropaque = (BTPageOpaque) PageGetSpecialPointer(rpage);
ropaque->btpo_prev = leftsib;
ropaque->btpo_next = rnext;
ropaque->btpo.level = xlrec->level;
ropaque->btpo_flags = isleaf ? BTP_LEAF : 0;
ropaque->btpo_cycleid = 0;
_bt_restore_page(rpage, datapos, datalen);
/*
* On leaf level, the high key of the left page is equal to the first key
* on the right page.
*/
if (isleaf)
{
ItemId hiItemId = PageGetItemId(rpage, P_FIRSTDATAKEY(ropaque));
left_hikey = PageGetItem(rpage, hiItemId);
left_hikeysz = ItemIdGetLength(hiItemId);
}
PageSetLSN(rpage, lsn);
MarkBufferDirty(rbuf);
/* don't release the buffer yet; we touch right page's first item below */
/* Now reconstruct left (original) sibling page */
if (XLogReadBufferForRedo(record, 0, &lbuf) == BLK_NEEDS_REDO)
{
/*
* To retain the same physical order of the tuples that they had, we
* initialize a temporary empty page for the left page and add all the
* items to that in item number order. This mirrors how _bt_split()
* works. It's not strictly required to retain the same physical
* order, as long as the items are in the correct item number order,
* but it helps debugging. See also _bt_restore_page(), which does
* the same for the right page.
*/
Page lpage = (Page) BufferGetPage(lbuf);
BTPageOpaque lopaque = (BTPageOpaque) PageGetSpecialPointer(lpage);
OffsetNumber off;
Item newitem = NULL;
Size newitemsz = 0;
Page newlpage;
OffsetNumber leftoff;
datapos = XLogRecGetBlockData(record, 0, &datalen);
if (onleft)
{
newitem = (Item) datapos;
newitemsz = MAXALIGN(IndexTupleSize(newitem));
datapos += newitemsz;
datalen -= newitemsz;
}
/* Extract left hikey and its size (assuming 16-bit alignment) */
if (!isleaf)
{
left_hikey = (Item) datapos;
left_hikeysz = MAXALIGN(IndexTupleSize(left_hikey));
datapos += left_hikeysz;
datalen -= left_hikeysz;
}
Assert(datalen == 0);
newlpage = PageGetTempPageCopySpecial(lpage);
/* Set high key */
leftoff = P_HIKEY;
if (PageAddItem(newlpage, left_hikey, left_hikeysz,
P_HIKEY, false, false) == InvalidOffsetNumber)
elog(PANIC, "failed to add high key to left page after split");
leftoff = OffsetNumberNext(leftoff);
for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstright; off++)
{
ItemId itemid;
Size itemsz;
Item item;
/* add the new item if it was inserted on left page */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
itemid = PageGetItemId(lpage, off);
itemsz = ItemIdGetLength(itemid);
item = PageGetItem(lpage, itemid);
if (PageAddItem(newlpage, item, itemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add old item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
/* cope with possibility that newitem goes at the end */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
PageRestoreTempPage(newlpage, lpage);
/* Fix opaque fields */
lopaque->btpo_flags = BTP_INCOMPLETE_SPLIT;
if (isleaf)
lopaque->btpo_flags |= BTP_LEAF;
lopaque->btpo_next = rightsib;
lopaque->btpo_cycleid = 0;
PageSetLSN(lpage, lsn);
MarkBufferDirty(lbuf);
}
/* We no longer need the buffers */
if (BufferIsValid(lbuf))
UnlockReleaseBuffer(lbuf);
UnlockReleaseBuffer(rbuf);
/*
* Fix left-link of the page to the right of the new right sibling.
*
* Note: in normal operation, we do this while still holding lock on the
* two split pages. However, that's not necessary for correctness in WAL
* replay, because no other index update can be in progress, and readers
* will cope properly when following an obsolete left-link.
*/
if (rnext != P_NONE)
{
Buffer buffer;
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buffer);
BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = rightsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
}
/*
* RelationGetBufferForTuple
*
* Returns pinned and exclusive-locked buffer of a page in given relation
* with free space >= given len.
*
* If otherBuffer is not InvalidBuffer, then it references a previously
* pinned buffer of another page in the same relation; on return, this
* buffer will also be exclusive-locked. (This case is used by heap_update;
* the otherBuffer contains the tuple being updated.)
*
* The reason for passing otherBuffer is that if two backends are doing
* concurrent heap_update operations, a deadlock could occur if they try
* to lock the same two buffers in opposite orders. To ensure that this
* can't happen, we impose the rule that buffers of a relation must be
* locked in increasing page number order. This is most conveniently done
* by having RelationGetBufferForTuple lock them both, with suitable care
* for ordering.
*
* NOTE: it is unlikely, but not quite impossible, for otherBuffer to be the
* same buffer we select for insertion of the new tuple (this could only
* happen if space is freed in that page after heap_update finds there's not
* enough there). In that case, the page will be pinned and locked only once.
*
* For the vmbuffer and vmbuffer_other arguments, we avoid deadlock by
* locking them only after locking the corresponding heap page, and taking
* no further lwlocks while they are locked.
*
* We normally use FSM to help us find free space. However,
* if HEAP_INSERT_SKIP_FSM is specified, we just append a new empty page to
* the end of the relation if the tuple won't fit on the current target page.
* This can save some cycles when we know the relation is new and doesn't
* contain useful amounts of free space.
*
* HEAP_INSERT_SKIP_FSM is also useful for non-WAL-logged additions to a
* relation, if the caller holds exclusive lock and is careful to invalidate
* relation's smgr_targblock before the first insertion --- that ensures that
* all insertions will occur into newly added pages and not be intermixed
* with tuples from other transactions. That way, a crash can't risk losing
* any committed data of other transactions. (See heap_insert's comments
* for additional constraints needed for safe usage of this behavior.)
*
* The caller can also provide a BulkInsertState object to optimize many
* insertions into the same relation. This keeps a pin on the current
* insertion target page (to save pin/unpin cycles) and also passes a
* BULKWRITE buffer selection strategy object to the buffer manager.
* Passing NULL for bistate selects the default behavior.
*
* We always try to avoid filling existing pages further than the fillfactor.
* This is OK since this routine is not consulted when updating a tuple and
* keeping it on the same page, which is the scenario fillfactor is meant
* to reserve space for.
*
* ereport(ERROR) is allowed here, so this routine *must* be called
* before any (unlogged) changes are made in buffer pool.
*/
Buffer
RelationGetBufferForTuple(Relation relation, Size len,
Buffer otherBuffer, int options,
BulkInsertState bistate,
Buffer *vmbuffer, Buffer *vmbuffer_other)
{
bool use_fsm = !(options & HEAP_INSERT_SKIP_FSM);
Buffer buffer = InvalidBuffer;
Page page;
Size pageFreeSpace,
saveFreeSpace;
BlockNumber targetBlock,
otherBlock;
bool needLock;
len = MAXALIGN(len); /* be conservative */
/* Bulk insert is not supported for updates, only inserts. */
Assert(otherBuffer == InvalidBuffer || !bistate);
/*
* If we're gonna fail for oversize tuple, do it right away
*/
if (len > MaxHeapTupleSize)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("row is too big: size %lu, maximum size %lu",
(unsigned long) len,
(unsigned long) MaxHeapTupleSize)));
/* Compute desired extra freespace due to fillfactor option */
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
if (otherBuffer != InvalidBuffer)
otherBlock = BufferGetBlockNumber(otherBuffer);
else
otherBlock = InvalidBlockNumber; /* just to keep compiler quiet */
/*
* We first try to put the tuple on the same page we last inserted a tuple
* on, as cached in the BulkInsertState or relcache entry. If that
* doesn't work, we ask the Free Space Map to locate a suitable page.
* Since the FSM's info might be out of date, we have to be prepared to
* loop around and retry multiple times. (To insure this isn't an infinite
* loop, we must update the FSM with the correct amount of free space on
* each page that proves not to be suitable.) If the FSM has no record of
* a page with enough free space, we give up and extend the relation.
*
* When use_fsm is false, we either put the tuple onto the existing target
* page or extend the relation.
*/
if (len + saveFreeSpace > MaxHeapTupleSize)
{
/* can't fit, don't bother asking FSM */
targetBlock = InvalidBlockNumber;
use_fsm = false;
}
else if (bistate && bistate->current_buf != InvalidBuffer)
targetBlock = BufferGetBlockNumber(bistate->current_buf);
else
targetBlock = RelationGetTargetBlock(relation);
if (targetBlock == InvalidBlockNumber && use_fsm)
{
/*
* We have no cached target page, so ask the FSM for an initial
* target.
*/
targetBlock = GetPageWithFreeSpace(relation, len + saveFreeSpace);
/*
* 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.
*/
if (targetBlock == InvalidBlockNumber)
{
BlockNumber nblocks = RelationGetNumberOfBlocks(relation);
if (nblocks > 0)
targetBlock = nblocks - 1;
}
}
while (targetBlock != InvalidBlockNumber)
{
/*
* Read and exclusive-lock the target block, as well as the other
* block if one was given, taking suitable care with lock ordering and
* the possibility they are the same block.
*
* If the page-level all-visible flag is set, caller will need to
* clear both that and the corresponding visibility map bit. However,
* by the time we return, we'll have x-locked the buffer, and we don't
* want to do any I/O while in that state. So we check the bit here
* before taking the lock, and pin the page if it appears necessary.
* Checking without the lock creates a risk of getting the wrong
* answer, so we'll have to recheck after acquiring the lock.
*/
if (otherBuffer == InvalidBuffer)
{
/* easy case */
buffer = ReadBufferBI(relation, targetBlock, bistate);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock == targetBlock)
{
/* also easy case */
buffer = otherBuffer;
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock < targetBlock)
{
/* lock other buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else
{
/* lock target buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
}
/*
* We now have the target page (and the other buffer, if any) pinned
* and locked. However, since our initial PageIsAllVisible checks
* were performed before acquiring the lock, the results might now be
* out of date, either for the selected victim buffer, or for the
* other buffer passed by the caller. In that case, we'll need to
* give up our locks, go get the pin(s) we failed to get earlier, and
* re-lock. That's pretty painful, but hopefully shouldn't happen
* often.
*
* Note that there's a small possibility that we didn't pin the page
* above but still have the correct page pinned anyway, either because
* we've already made a previous pass through this loop, or because
* caller passed us the right page anyway.
*
* Note also that it's possible that by the time we get the pin and
* retake the buffer locks, the visibility map bit will have been
* cleared by some other backend anyway. In that case, we'll have
* done a bit of extra work for no gain, but there's no real harm
* done.
*/
if (otherBuffer == InvalidBuffer || buffer <= otherBuffer)
GetVisibilityMapPins(relation, buffer, otherBuffer,
targetBlock, otherBlock, vmbuffer,
vmbuffer_other);
else
GetVisibilityMapPins(relation, otherBuffer, buffer,
otherBlock, targetBlock, vmbuffer_other,
vmbuffer);
/*
* Now we can check to see if there's enough free space here. If so,
* we're done.
*/
page = BufferGetPage(buffer);
pageFreeSpace = PageGetHeapFreeSpace(page);
if (len + saveFreeSpace <= pageFreeSpace)
{
/* use this page as future insert target, too */
RelationSetTargetBlock(relation, targetBlock);
return buffer;
}
/*
* Not enough space, so we must give up our page locks and pin (if
* any) and prepare to look elsewhere. We don't care which order we
* unlock the two buffers in, so this can be slightly simpler than the
* code above.
*/
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
if (otherBuffer == InvalidBuffer)
ReleaseBuffer(buffer);
else if (otherBlock != targetBlock)
{
LockBuffer(otherBuffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
/* Without FSM, always fall out of the loop and extend */
if (!use_fsm)
break;
/*
* Update FSM as to condition of this page, and ask for another page
* to try.
*/
targetBlock = RecordAndGetPageWithFreeSpace(relation,
targetBlock,
pageFreeSpace,
len + saveFreeSpace);
}
/*
* Have to extend the relation.
*
* We have to use a lock to ensure no one else is extending the rel at the
* same time, else we will both try to initialize the same new page. We
* can skip locking for new or temp relations, however, since no one else
* could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(relation);
if (needLock)
LockRelationForExtension(relation, ExclusiveLock);
/*
* XXX This does an lseek - rather expensive - but at the moment it is the
* only way to accurately determine how many blocks are in a relation. Is
* it worth keeping an accurate file length in shared memory someplace,
* rather than relying on the kernel to do it for us?
*/
buffer = ReadBufferBI(relation, P_NEW, bistate);
/*
* We can be certain that locking the otherBuffer first is OK, since it
* must have a lower page number.
*/
if (otherBuffer != InvalidBuffer)
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
/*
* Now acquire lock on the new page.
*/
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/*
* Release the file-extension lock; it's now OK for someone else to extend
* the relation some more. Note that we cannot release this lock before
* we have buffer lock on the new page, or we risk a race condition
* against vacuumlazy.c --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(relation, ExclusiveLock);
/*
* We need to initialize the empty new page. Double-check that it really
* is empty (this should never happen, but if it does we don't want to
* risk wiping out valid data).
*/
page = BufferGetPage(buffer);
if (!PageIsNew(page))
elog(ERROR, "page %u of relation \"%s\" should be empty but is not",
BufferGetBlockNumber(buffer),
RelationGetRelationName(relation));
PageInit(page, BufferGetPageSize(buffer), 0);
if (len > PageGetHeapFreeSpace(page))
{
/* We should not get here given the test at the top */
elog(PANIC, "tuple is too big: size %lu", (unsigned long) len);
}
/*
* Remember the new page as our target for future insertions.
*
* XXX should we enter the new page into the free space map immediately,
* or just keep it for this backend's exclusive use in the short run
* (until VACUUM sees it)? Seems to depend on whether you expect the
* current backend to make more insertions or not, which is probably a
* good bet most of the time. So for now, don't add it to FSM yet.
*/
RelationSetTargetBlock(relation, BufferGetBlockNumber(buffer));
return buffer;
}
static void
ginRedoUpdateMetapage(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
ginxlogUpdateMeta *data = (ginxlogUpdateMeta *) XLogRecGetData(record);
Buffer metabuffer;
Page metapage;
Buffer buffer;
/*
* Restore the metapage. This is essentially the same as a full-page
* image, so restore the metapage unconditionally without looking at the
* LSN, to avoid torn page hazards.
*/
metabuffer = XLogInitBufferForRedo(record, 0);
Assert(BufferGetBlockNumber(metabuffer) == GIN_METAPAGE_BLKNO);
metapage = BufferGetPage(metabuffer);
GinInitPage(metapage, GIN_META, BufferGetPageSize(metabuffer));
memcpy(GinPageGetMeta(metapage), &data->metadata, sizeof(GinMetaPageData));
PageSetLSN(metapage, lsn);
MarkBufferDirty(metabuffer);
if (data->ntuples > 0)
{
/*
* insert into tail page
*/
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
OffsetNumber off;
int i;
Size tupsize;
char *payload;
IndexTuple tuples;
Size totaltupsize;
payload = XLogRecGetBlockData(record, 1, &totaltupsize);
tuples = (IndexTuple) payload;
if (PageIsEmpty(page))
off = FirstOffsetNumber;
else
off = OffsetNumberNext(PageGetMaxOffsetNumber(page));
for (i = 0; i < data->ntuples; i++)
{
tupsize = IndexTupleSize(tuples);
if (PageAddItem(page, (Item) tuples, tupsize, off,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page");
tuples = (IndexTuple) (((char *) tuples) + tupsize);
off++;
}
Assert(payload + totaltupsize == (char *) tuples);
/*
* Increase counter of heap tuples
*/
GinPageGetOpaque(page)->maxoff++;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
else if (data->prevTail != InvalidBlockNumber)
{
/*
* New tail
*/
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
GinPageGetOpaque(page)->rightlink = data->newRightlink;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
UnlockReleaseBuffer(metabuffer);
}
/*
* _bt_getbuf() -- Get a buffer by block number for read or write.
*
* blkno == P_NEW means to get an unallocated index page. The page
* will be initialized before returning it.
*
* When this routine returns, the appropriate lock is set on the
* requested buffer and its reference count has been incremented
* (ie, the buffer is "locked and pinned"). Also, we apply
* _bt_checkpage to sanity-check the page (except in P_NEW case).
*/
Buffer
_bt_getbuf(Relation rel, BlockNumber blkno, int access)
{
Buffer buf;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
if (blkno != P_NEW)
{
/* Read an existing block of the relation */
buf = ReadBuffer(rel, blkno);
LockBuffer(buf, access);
_bt_checkpage(rel, buf);
}
else
{
bool needLock;
Page page;
Assert(access == BT_WRITE);
/*
* First see if the FSM knows of any free pages.
*
* We can't trust the FSM's report unreservedly; we have to check that
* the page is still free. (For example, an already-free page could
* have been re-used between the time the last VACUUM scanned it and
* the time the VACUUM made its FSM updates.)
*
* In fact, it's worse than that: we can't even assume that it's safe
* to take a lock on the reported page. If somebody else has a lock
* on it, or even worse our own caller does, we could deadlock. (The
* own-caller scenario is actually not improbable. Consider an index
* on a serial or timestamp column. Nearly all splits will be at the
* rightmost page, so it's entirely likely that _bt_split will call us
* while holding a lock on the page most recently acquired from FSM. A
* VACUUM running concurrently with the previous split could well have
* placed that page back in FSM.)
*
* To get around that, we ask for only a conditional lock on the
* reported page. If we fail, then someone else is using the page,
* and we may reasonably assume it's not free. (If we happen to be
* wrong, the worst consequence is the page will be lost to use till
* the next VACUUM, which is no big problem.)
*/
for (;;)
{
blkno = GetFreeIndexPage(&rel->rd_node);
if (blkno == InvalidBlockNumber)
break;
buf = ReadBuffer(rel, blkno);
if (ConditionalLockBuffer(buf))
{
page = BufferGetPage(buf);
if (_bt_page_recyclable(page))
{
/* Okay to use page. Re-initialize and return it */
_bt_pageinit(page, BufferGetPageSize(buf));
return buf;
}
elog(DEBUG2, "FSM returned nonrecyclable page");
_bt_relbuf(rel, buf);
}
else
{
elog(DEBUG2, "FSM returned nonlockable page");
/* couldn't get lock, so just drop pin */
ReleaseBuffer(buf);
}
}
/*
* Extend the relation by one page.
*
* We have to use a lock to ensure no one else is extending the rel at
* the same time, else we will both try to initialize the same new
* page. We can skip locking for new or temp relations, however,
* since no one else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
buf = ReadBuffer(rel, P_NEW);
/* Acquire buffer lock on new page */
LockBuffer(buf, BT_WRITE);
/*
* Release the file-extension lock; it's now OK for someone else to
* extend the relation some more. Note that we cannot release this
* lock before we have buffer lock on the new page, or we risk a race
* condition against btvacuumscan --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Initialize the new page before returning it */
page = BufferGetPage(buf);
Assert(PageIsNew((PageHeader) page));
_bt_pageinit(page, BufferGetPageSize(buf));
}
/* ref count and lock type are correct */
return buf;
}
/*
* _hash_splitbucket -- split 'obucket' into 'obucket' and 'nbucket'
*
* We are splitting a bucket that consists of a base bucket page and zero
* or more overflow (bucket chain) pages. We must relocate tuples that
* belong in the new bucket, and compress out any free space in the old
* bucket.
*
* The caller must hold exclusive locks on both buckets to ensure that
* no one else is trying to access them (see README).
*
* The caller must hold a pin, but no lock, on the metapage buffer.
* The buffer is returned in the same state. (The metapage is only
* touched if it becomes necessary to add or remove overflow pages.)
*/
static void
_hash_splitbucket(Relation rel,
Buffer metabuf,
Bucket obucket,
Bucket nbucket,
BlockNumber start_oblkno,
BlockNumber start_nblkno,
uint32 maxbucket,
uint32 highmask,
uint32 lowmask)
{
Bucket bucket;
Buffer obuf;
Buffer nbuf;
BlockNumber oblkno;
BlockNumber nblkno;
bool null;
Datum datum;
HashItem hitem;
HashPageOpaque oopaque;
HashPageOpaque nopaque;
IndexTuple itup;
Size itemsz;
OffsetNumber ooffnum;
OffsetNumber noffnum;
OffsetNumber omaxoffnum;
Page opage;
Page npage;
TupleDesc itupdesc = RelationGetDescr(rel);
/*
* It should be okay to simultaneously write-lock pages from each
* bucket, since no one else can be trying to acquire buffer lock
* on pages of either bucket.
*/
oblkno = start_oblkno;
nblkno = start_nblkno;
obuf = _hash_getbuf(rel, oblkno, HASH_WRITE);
nbuf = _hash_getbuf(rel, nblkno, HASH_WRITE);
opage = BufferGetPage(obuf);
npage = BufferGetPage(nbuf);
_hash_checkpage(rel, opage, LH_BUCKET_PAGE);
oopaque = (HashPageOpaque) PageGetSpecialPointer(opage);
/* initialize the new bucket's primary page */
_hash_pageinit(npage, BufferGetPageSize(nbuf));
nopaque = (HashPageOpaque) PageGetSpecialPointer(npage);
nopaque->hasho_prevblkno = InvalidBlockNumber;
nopaque->hasho_nextblkno = InvalidBlockNumber;
nopaque->hasho_bucket = nbucket;
nopaque->hasho_flag = LH_BUCKET_PAGE;
nopaque->hasho_filler = HASHO_FILL;
/*
* Partition the tuples in the old bucket between the old bucket and the
* new bucket, advancing along the old bucket's overflow bucket chain
* and adding overflow pages to the new bucket as needed.
*/
ooffnum = FirstOffsetNumber;
omaxoffnum = PageGetMaxOffsetNumber(opage);
for (;;)
{
/*
* at each iteration through this loop, each of these variables
* should be up-to-date: obuf opage oopaque ooffnum omaxoffnum
*/
/* check if we're at the end of the page */
if (ooffnum > omaxoffnum)
{
/* at end of page, but check for an(other) overflow page */
oblkno = oopaque->hasho_nextblkno;
if (!BlockNumberIsValid(oblkno))
break;
/*
* we ran out of tuples on this particular page, but we
* have more overflow pages; advance to next page.
*/
_hash_wrtbuf(rel, obuf);
obuf = _hash_getbuf(rel, oblkno, HASH_WRITE);
opage = BufferGetPage(obuf);
_hash_checkpage(rel, opage, LH_OVERFLOW_PAGE);
oopaque = (HashPageOpaque) PageGetSpecialPointer(opage);
ooffnum = FirstOffsetNumber;
omaxoffnum = PageGetMaxOffsetNumber(opage);
continue;
}
/*
* Re-hash the tuple to determine which bucket it now belongs in.
*
* It is annoying to call the hash function while holding locks,
* but releasing and relocking the page for each tuple is unappealing
* too.
*/
hitem = (HashItem) PageGetItem(opage, PageGetItemId(opage, ooffnum));
itup = &(hitem->hash_itup);
datum = index_getattr(itup, 1, itupdesc, &null);
Assert(!null);
bucket = _hash_hashkey2bucket(_hash_datum2hashkey(rel, datum),
maxbucket, highmask, lowmask);
if (bucket == nbucket)
{
/*
* insert the tuple into the new bucket. if it doesn't fit on
* the current page in the new bucket, we must allocate a new
* overflow page and place the tuple on that page instead.
*/
itemsz = IndexTupleDSize(hitem->hash_itup)
+ (sizeof(HashItemData) - sizeof(IndexTupleData));
itemsz = MAXALIGN(itemsz);
if (PageGetFreeSpace(npage) < itemsz)
{
/* write out nbuf and drop lock, but keep pin */
_hash_chgbufaccess(rel, nbuf, HASH_WRITE, HASH_NOLOCK);
/* chain to a new overflow page */
nbuf = _hash_addovflpage(rel, metabuf, nbuf);
npage = BufferGetPage(nbuf);
_hash_checkpage(rel, npage, LH_OVERFLOW_PAGE);
/* we don't need nopaque within the loop */
}
noffnum = OffsetNumberNext(PageGetMaxOffsetNumber(npage));
if (PageAddItem(npage, (Item) hitem, itemsz, noffnum, LP_USED)
== InvalidOffsetNumber)
elog(ERROR, "failed to add index item to \"%s\"",
RelationGetRelationName(rel));
/*
* now delete the tuple from the old bucket. after this
* section of code, 'ooffnum' will actually point to the
* ItemId to which we would point if we had advanced it before
* the deletion (PageIndexTupleDelete repacks the ItemId
* array). this also means that 'omaxoffnum' is exactly one
* less than it used to be, so we really can just decrement it
* instead of calling PageGetMaxOffsetNumber.
*/
PageIndexTupleDelete(opage, ooffnum);
omaxoffnum = OffsetNumberPrev(omaxoffnum);
}
else
{
/*
* the tuple stays on this page. we didn't move anything, so
* we didn't delete anything and therefore we don't have to
* change 'omaxoffnum'.
*/
Assert(bucket == obucket);
ooffnum = OffsetNumberNext(ooffnum);
}
}
/*
* We're at the end of the old bucket chain, so we're done partitioning
* the tuples. Before quitting, call _hash_squeezebucket to ensure the
* tuples remaining in the old bucket (including the overflow pages) are
* packed as tightly as possible. The new bucket is already tight.
*/
_hash_wrtbuf(rel, obuf);
_hash_wrtbuf(rel, nbuf);
_hash_squeezebucket(rel, obucket, start_oblkno);
}
/*
* 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))));
}
/*
* 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, List *updated_stats)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber nblocks,
blkno;
HeapTupleData tuple;
char *relname;
BlockNumber empty_pages,
vacuumed_pages;
double num_tuples,
tups_vacuumed,
nkeep,
nunused;
IndexBulkDeleteResult **indstats;
int i;
int reindex_count = 1;
PGRUsage ru0;
/* Fetch gp_persistent_relation_node information that will be added to XLOG record. */
RelationFetchGpRelationNodeForXLog(onerel);
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->nonempty_pages = 0;
lazy_space_alloc(vacrelstats, nblocks);
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;
vacuum_delay_point();
/*
* 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)
{
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i], &indstats[i], vacrelstats);
reindex_count++;
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
/* Forget the now-vacuumed tuples, and press on */
vacrelstats->num_dead_tuples = 0;
vacrelstats->num_index_scans++;
}
/* -------- MirroredLock ---------- */
MIRROREDLOCK_BUFMGR_LOCK;
buf = ReadBufferWithStrategy(onerel, blkno, 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);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
LockRelationForExtension(onerel, ExclusiveLock);
UnlockRelationForExtension(onerel, ExclusiveLock);
/* -------- MirroredLock ---------- */
MIRROREDLOCK_BUFMGR_LOCK;
LockBufferForCleanup(buf);
if (PageIsNew(page))
{
ereport(WARNING,
(errmsg("relation \"%s\" page %u is uninitialized --- fixing",
relname, blkno)));
PageInit(page, BufferGetPageSize(buf), 0);
/* must record in xlog so that changetracking will know about this change */
log_heap_newpage(onerel, page, blkno);
empty_pages++;
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
}
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
continue;
}
if (PageIsEmpty(page))
{
empty_pages++;
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
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, false);
/*
* Now scan the page to collect vacuumable items and check for tuples
* requiring freezing.
*/
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));
continue;
}
Assert(ItemIdIsNormal(itemid));
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tupgone = false;
switch (HeapTupleSatisfiesVacuum(onerel, 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 */
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);
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must not remove it
* from relation.
*/
nkeep += 1;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (tupgone)
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
tups_vacuumed += 1;
}
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, false))
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);
/* no XLOG for temp tables, though */
if (!onerel->rd_istemp)
{
XLogRecPtr recptr;
recptr = log_heap_freeze(onerel, buf, FreezeLimit,
frozen, nfrozen);
PageSetLSN(page, recptr);
}
}
/*
* 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 */
vacrelstats->num_dead_tuples = 0;
vacuumed_pages++;
}
/*
* 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)
{
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
}
/* Remember the location of the last page with nonremovable tuples */
if (hastup)
vacrelstats->nonempty_pages = blkno + 1;
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
}
/* save stats for use later */
vacrelstats->rel_tuples = num_tuples;
vacrelstats->tuples_deleted = tups_vacuumed;
/* 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)
{
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i], &indstats[i], vacrelstats);
reindex_count++;
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
vacrelstats->num_index_scans++;
}
/* Do post-vacuum cleanup and statistics update for each index */
for (i = 0; i < nindexes; i++)
lazy_cleanup_index(Irel[i], indstats[i], vacrelstats, updated_stats);
/* 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 pages",
RelationGetRelationName(onerel),
tups_vacuumed, num_tuples, nblocks),
errdetail("%.0f dead row versions cannot be removed yet.\n"
"There were %.0f unused item pointers.\n"
"%u pages contain useful free space.\n"
"%u pages are entirely empty.\n"
"%s.",
nkeep,
nunused,
vacrelstats->tot_free_pages,
empty_pages,
pg_rusage_show(&ru0))));
}