/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
* or InvalidXLogRecPtr in normal running. The page LSN is advanced to the
* one provided; in normal running, we generate a new XLOG record and set the
* page LSN to that value. cutoff_xid is the largest xmin on the page being
* marked all-visible; it is needed for Hot Standby, and can be
* InvalidTransactionId if the page contains no tuples.
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, XLogRecPtr recptr,
Buffer buf, TransactionId cutoff_xid)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
/* Check that we have the right page pinned */
if (!BufferIsValid(buf) || BufferGetBlockNumber(buf) != mapBlock)
elog(ERROR, "wrong buffer passed to visibilitymap_set");
page = BufferGetPage(buf);
map = PageGetContents(page);
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
START_CRIT_SECTION();
map[mapByte] |= (1 << mapBit);
MarkBufferDirty(buf);
if (RelationNeedsWAL(rel))
{
if (XLogRecPtrIsInvalid(recptr))
recptr = log_heap_visible(rel->rd_node, heapBlk, buf,
cutoff_xid);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
END_CRIT_SECTION();
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
static void
gistRedoCreateIndex(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer buffer;
Page page;
buffer = XLogInitBufferForRedo(record, 0);
Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
page = (Page) BufferGetPage(buffer);
GISTInitBuffer(buffer, F_LEAF);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
static void
ginRedoClearIncompleteSplit(XLogReaderState *record, uint8 block_id)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer buffer;
Page page;
if (XLogReadBufferForRedo(record, block_id, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
GinPageGetOpaque(page)->flags &= ~GIN_INCOMPLETE_SPLIT;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
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);
}
static void
gistRedoCreateIndex(XLogRecPtr lsn, XLogRecord *record)
{
RelFileNode *node = (RelFileNode *) XLogRecGetData(record);
Buffer buffer;
Page page;
buffer = XLogReadBuffer(*node, GIST_ROOT_BLKNO, true);
Assert(BufferIsValid(buffer));
page = (Page) BufferGetPage(buffer);
GISTInitBuffer(buffer, F_LEAF);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/*
* gistbuildempty() -- build an empty gist index in the initialization fork
*/
void
gistbuildempty(Relation index)
{
Buffer buffer;
/* Initialize the root page */
buffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/* Initialize and xlog buffer */
START_CRIT_SECTION();
GISTInitBuffer(buffer, F_LEAF);
MarkBufferDirty(buffer);
log_newpage_buffer(buffer, true);
END_CRIT_SECTION();
/* Unlock and release the buffer */
UnlockReleaseBuffer(buffer);
}
/*
* Write the given statistics to the index's metapage
*
* Note: nPendingPages and ginVersion are *not* copied over
*/
void
ginUpdateStats(Relation index, const GinStatsData *stats)
{
Buffer metabuffer;
Page metapage;
GinMetaPageData *metadata;
metabuffer = ReadBuffer(index, GIN_METAPAGE_BLKNO);
LockBuffer(metabuffer, GIN_EXCLUSIVE);
metapage = BufferGetPage(metabuffer);
metadata = GinPageGetMeta(metapage);
START_CRIT_SECTION();
metadata->nTotalPages = stats->nTotalPages;
metadata->nEntryPages = stats->nEntryPages;
metadata->nDataPages = stats->nDataPages;
metadata->nEntries = stats->nEntries;
MarkBufferDirty(metabuffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
ginxlogUpdateMeta data;
data.node = index->rd_node;
data.ntuples = 0;
data.newRightlink = data.prevTail = InvalidBlockNumber;
memcpy(&data.metadata, metadata, sizeof(GinMetaPageData));
XLogBeginInsert();
XLogRegisterData((char *) &data, sizeof(ginxlogUpdateMeta));
XLogRegisterBuffer(0, metabuffer, REGBUF_WILL_INIT);
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE);
PageSetLSN(metapage, recptr);
}
UnlockReleaseBuffer(metabuffer);
END_CRIT_SECTION();
}
/*
* _bt_clear_incomplete_split -- clear INCOMPLETE_SPLIT flag on a page
*
* This is a common subroutine of the redo functions of all the WAL record
* types that can insert a downlink: insert, split, and newroot.
*/
static void
_bt_clear_incomplete_split(XLogReaderState *record, uint8 block_id)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer buf;
if (XLogReadBufferForRedo(record, block_id, &buf) == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buf);
BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);
Assert((pageop->btpo_flags & BTP_INCOMPLETE_SPLIT) != 0);
pageop->btpo_flags &= ~BTP_INCOMPLETE_SPLIT;
PageSetLSN(page, lsn);
MarkBufferDirty(buf);
}
if (BufferIsValid(buf))
UnlockReleaseBuffer(buf);
}
/*
* replay a hash index meta page
*/
static void
hash_xlog_init_meta_page(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
Page page;
Buffer metabuf;
xl_hash_init_meta_page *xlrec = (xl_hash_init_meta_page *) XLogRecGetData(record);
/* create the index' metapage */
metabuf = XLogInitBufferForRedo(record, 0);
Assert(BufferIsValid(metabuf));
_hash_init_metabuffer(metabuf, xlrec->num_tuples, xlrec->procid,
xlrec->ffactor, true);
page = (Page) BufferGetPage(metabuf);
PageSetLSN(page, lsn);
MarkBufferDirty(metabuf);
/* all done */
UnlockReleaseBuffer(metabuf);
}
void
brinbuildempty(Relation index)
{
Buffer metabuf;
/* An empty BRIN index has a metapage only. */
metabuf =
ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);
/* Initialize and xlog metabuffer. */
START_CRIT_SECTION();
brin_metapage_init(BufferGetPage(metabuf), BrinGetPagesPerRange(index),
BRIN_CURRENT_VERSION);
MarkBufferDirty(metabuf);
log_newpage_buffer(metabuf, false);
END_CRIT_SECTION();
UnlockReleaseBuffer(metabuf);
}
static void
ginRedoClearIncompleteSplit(XLogRecPtr lsn, RelFileNode node, BlockNumber blkno)
{
Buffer buffer;
Page page;
buffer = XLogReadBuffer(node, blkno, false);
if (!BufferIsValid(buffer))
return; /* page was deleted, nothing to do */
page = (Page) BufferGetPage(buffer);
if (lsn > PageGetLSN(page))
{
GinPageGetOpaque(page)->flags &= ~GIN_INCOMPLETE_SPLIT;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
/*
* replay split cleanup flag operation for primary bucket page.
*/
static void
hash_xlog_split_cleanup(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer buffer;
Page page;
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
HashPageOpaque bucket_opaque;
page = (Page) BufferGetPage(buffer);
bucket_opaque = (HashPageOpaque) PageGetSpecialPointer(page);
bucket_opaque->hasho_flag &= ~LH_BUCKET_NEEDS_SPLIT_CLEANUP;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
static void
gistRedoCreateIndex(XLogRecPtr lsn, XLogRecord *record)
{
RelFileNode *node = (RelFileNode *) XLogRecGetData(record);
Buffer buffer;
Page page;
/* Backup blocks are not used in create_index records */
Assert(!(record->xl_info & XLR_BKP_BLOCK_MASK));
buffer = XLogReadBuffer(*node, GIST_ROOT_BLKNO, true);
Assert(BufferIsValid(buffer));
page = (Page) BufferGetPage(buffer);
GISTInitBuffer(buffer, F_LEAF);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
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);
}
/*
* replay for update meta page
*/
static void
hash_xlog_update_meta_page(XLogReaderState *record)
{
HashMetaPage metap;
XLogRecPtr lsn = record->EndRecPtr;
xl_hash_update_meta_page *xldata = (xl_hash_update_meta_page *) XLogRecGetData(record);
Buffer metabuf;
Page page;
if (XLogReadBufferForRedo(record, 0, &metabuf) == BLK_NEEDS_REDO)
{
page = BufferGetPage(metabuf);
metap = HashPageGetMeta(page);
metap->hashm_ntuples = xldata->ntuples;
PageSetLSN(page, lsn);
MarkBufferDirty(metabuf);
}
if (BufferIsValid(metabuf))
UnlockReleaseBuffer(metabuf);
}
/*
* gistbuildempty() -- build an empty gist index in the initialization fork
*/
Datum
gistbuildempty(PG_FUNCTION_ARGS)
{
Relation index = (Relation) PG_GETARG_POINTER(0);
Buffer buffer;
/* Initialize the root page */
buffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/* Initialize and xlog buffer */
START_CRIT_SECTION();
GISTInitBuffer(buffer, F_LEAF);
MarkBufferDirty(buffer);
log_newpage_buffer(buffer, true);
END_CRIT_SECTION();
/* Unlock and release the buffer */
UnlockReleaseBuffer(buffer);
PG_RETURN_VOID();
}
/*
* This is functionally the same as heap_xlog_newpage.
*/
static void
ginRedoVacuumPage(XLogRecPtr lsn, XLogRecord *record)
{
ginxlogVacuumPage *xlrec = (ginxlogVacuumPage *) XLogRecGetData(record);
char *blk = ((char *) xlrec) + sizeof(ginxlogVacuumPage);
Buffer buffer;
Page page;
Assert(xlrec->hole_offset < BLCKSZ);
Assert(xlrec->hole_length < BLCKSZ);
/* Backup blocks are not used, we'll re-initialize the page always. */
Assert(!(record->xl_info & XLR_BKP_BLOCK_MASK));
buffer = XLogReadBuffer(xlrec->node, xlrec->blkno, true);
if (!BufferIsValid(buffer))
return;
page = (Page) BufferGetPage(buffer);
if (xlrec->hole_length == 0)
{
memcpy((char *) page, blk, BLCKSZ);
}
else
{
memcpy((char *) page, blk, xlrec->hole_offset);
/* must zero-fill the hole */
MemSet((char *) page + xlrec->hole_offset, 0, xlrec->hole_length);
memcpy((char *) page + (xlrec->hole_offset + xlrec->hole_length),
blk + xlrec->hole_offset,
BLCKSZ - (xlrec->hole_offset + xlrec->hole_length));
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
static void
gistRedoPageDeleteRecord(XLogRecPtr lsn, XLogRecord *record)
{
gistxlogPageDelete *xldata = (gistxlogPageDelete *) XLogRecGetData(record);
Buffer buffer;
Page page;
/* nothing else to do if page was backed up (and no info to do it with) */
if (record->xl_info & XLR_BKP_BLOCK_1)
return;
buffer = XLogReadBuffer(xldata->node, xldata->blkno, false);
if (!BufferIsValid(buffer))
return;
page = (Page) BufferGetPage(buffer);
GistPageSetDeleted(page);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/*
* Initialize a page as an empty regular BRIN page, WAL-log this, and record
* the page in FSM.
*
* There are several corner situations in which we extend the relation to
* obtain a new page and later find that we cannot use it immediately. When
* that happens, we don't want to leave the page go unrecorded in FSM, because
* there is no mechanism to get the space back and the index would bloat.
* Also, because we would not WAL-log the action that would initialize the
* page, the page would go uninitialized in a standby (or after recovery).
*/
static void
brin_initialize_empty_new_buffer(Relation idxrel, Buffer buffer)
{
Page page;
BRIN_elog((DEBUG2,
"brin_initialize_empty_new_buffer: initializing blank page %u",
BufferGetBlockNumber(buffer)));
START_CRIT_SECTION();
page = BufferGetPage(buffer);
brin_page_init(page, BRIN_PAGETYPE_REGULAR);
MarkBufferDirty(buffer);
log_newpage_buffer(buffer, true);
END_CRIT_SECTION();
/*
* We update the FSM for this page, but this is not WAL-logged. This is
* acceptable because VACUUM will scan the index and update the FSM with
* pages whose FSM records were forgotten in a crash.
*/
RecordPageWithFreeSpace(idxrel, BufferGetBlockNumber(buffer),
br_page_get_freespace(page));
}
static void
ginRedoVacuumDataLeafPage(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer buffer;
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
Size len;
ginxlogVacuumDataLeafPage *xlrec;
xlrec = (ginxlogVacuumDataLeafPage *) XLogRecGetBlockData(record, 0, &len);
Assert(GinPageIsLeaf(page));
Assert(GinPageIsData(page));
ginRedoRecompress(page, &xlrec->data);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/*
* 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))));
}
IndexBuildResult *
ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
GinBuildState buildstate;
Buffer RootBuffer,
MetaBuffer;
ItemPointerData *list;
Datum key;
GinNullCategory category;
uint32 nlist;
MemoryContext oldCtx;
OffsetNumber attnum;
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
initGinState(&buildstate.ginstate, index);
buildstate.indtuples = 0;
memset(&buildstate.buildStats, 0, sizeof(GinStatsData));
/* initialize the meta page */
MetaBuffer = GinNewBuffer(index);
/* initialize the root page */
RootBuffer = GinNewBuffer(index);
START_CRIT_SECTION();
GinInitMetabuffer(MetaBuffer);
MarkBufferDirty(MetaBuffer);
GinInitBuffer(RootBuffer, GIN_LEAF);
MarkBufferDirty(RootBuffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
Page page;
XLogBeginInsert();
XLogRegisterBuffer(0, MetaBuffer, REGBUF_WILL_INIT | REGBUF_STANDARD);
XLogRegisterBuffer(1, RootBuffer, REGBUF_WILL_INIT);
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_INDEX);
page = BufferGetPage(RootBuffer);
PageSetLSN(page, recptr);
page = BufferGetPage(MetaBuffer);
PageSetLSN(page, recptr);
}
UnlockReleaseBuffer(MetaBuffer);
UnlockReleaseBuffer(RootBuffer);
END_CRIT_SECTION();
/* count the root as first entry page */
buildstate.buildStats.nEntryPages++;
/*
* create a temporary memory context that is used to hold data not yet
* dumped out to the index
*/
buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Gin build temporary context",
ALLOCSET_DEFAULT_SIZES);
/*
* create a temporary memory context that is used for calling
* ginExtractEntries(), and can be reset after each tuple
*/
buildstate.funcCtx = AllocSetContextCreate(CurrentMemoryContext,
"Gin build temporary context for user-defined function",
ALLOCSET_DEFAULT_SIZES);
buildstate.accum.ginstate = &buildstate.ginstate;
ginInitBA(&buildstate.accum);
/*
* Do the heap scan. We disallow sync scan here because dataPlaceToPage
* prefers to receive tuples in TID order.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, false,
ginBuildCallback, (void *) &buildstate, NULL);
/* dump remaining entries to the index */
oldCtx = MemoryContextSwitchTo(buildstate.tmpCtx);
ginBeginBAScan(&buildstate.accum);
while ((list = ginGetBAEntry(&buildstate.accum,
&attnum, &key, &category, &nlist)) != NULL)
{
/* there could be many entries, so be willing to abort here */
CHECK_FOR_INTERRUPTS();
ginEntryInsert(&buildstate.ginstate, attnum, key, category,
list, nlist, &buildstate.buildStats);
}
MemoryContextSwitchTo(oldCtx);
MemoryContextDelete(buildstate.funcCtx);
MemoryContextDelete(buildstate.tmpCtx);
/*
* Update metapage stats
*/
buildstate.buildStats.nTotalPages = RelationGetNumberOfBlocks(index);
ginUpdateStats(index, &buildstate.buildStats);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
/*
* Main entry point to GiST index build. Initially calls insert over and over,
* but switches to more efficient buffering build algorithm after a certain
* number of tuples (unless buffering mode is disabled).
*/
Datum
gistbuild(PG_FUNCTION_ARGS)
{
Relation heap = (Relation) PG_GETARG_POINTER(0);
Relation index = (Relation) PG_GETARG_POINTER(1);
IndexInfo *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
IndexBuildResult *result;
double reltuples;
GISTBuildState buildstate;
Buffer buffer;
Page page;
MemoryContext oldcxt = CurrentMemoryContext;
int fillfactor;
buildstate.indexrel = index;
if (index->rd_options)
{
/* Get buffering mode from the options string */
GiSTOptions *options = (GiSTOptions *) index->rd_options;
char *bufferingMode = (char *) options + options->bufferingModeOffset;
if (strcmp(bufferingMode, "on") == 0)
buildstate.bufferingMode = GIST_BUFFERING_STATS;
else if (strcmp(bufferingMode, "off") == 0)
buildstate.bufferingMode = GIST_BUFFERING_DISABLED;
else
buildstate.bufferingMode = GIST_BUFFERING_AUTO;
fillfactor = options->fillfactor;
}
else
{
/*
* By default, switch to buffering mode when the index grows too large
* to fit in cache.
*/
buildstate.bufferingMode = GIST_BUFFERING_AUTO;
fillfactor = GIST_DEFAULT_FILLFACTOR;
}
/* Calculate target amount of free space to leave on pages */
buildstate.freespace = BLCKSZ * (100 - fillfactor) / 100;
/*
* We expect to be called exactly once for any index relation. If that's
* not the case, big trouble's what we have.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/* no locking is needed */
buildstate.giststate = initGISTstate(index);
/*
* Create a temporary memory context that is reset once for each tuple
* processed. (Note: we don't bother to make this a child of the
* giststate's scanCxt, so we have to delete it separately at the end.)
*/
buildstate.giststate->tempCxt = createTempGistContext();
/* initialize the root page */
buffer = gistNewBuffer(index);
Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
page = BufferGetPage(buffer);
START_CRIT_SECTION();
GISTInitBuffer(buffer, F_LEAF);
MarkBufferDirty(buffer);
if (RelationNeedsWAL(index))
{
XLogRecPtr recptr;
XLogRecData rdata;
rdata.data = (char *) &(index->rd_node);
rdata.len = sizeof(RelFileNode);
rdata.buffer = InvalidBuffer;
rdata.next = NULL;
recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX, &rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
else
PageSetLSN(page, gistGetFakeLSN(heap));
UnlockReleaseBuffer(buffer);
END_CRIT_SECTION();
/* build the index */
buildstate.indtuples = 0;
buildstate.indtuplesSize = 0;
/*
* Do the heap scan.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
gistBuildCallback, (void *) &buildstate);
/*
* If buffering was used, flush out all the tuples that are still in the
* buffers.
*/
if (buildstate.bufferingMode == GIST_BUFFERING_ACTIVE)
{
elog(DEBUG1, "all tuples processed, emptying buffers");
gistEmptyAllBuffers(&buildstate);
gistFreeBuildBuffers(buildstate.gfbb);
}
/* okay, all heap tuples are indexed */
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(buildstate.giststate->tempCxt);
freeGISTstate(buildstate.giststate);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = (double) buildstate.indtuples;
PG_RETURN_POINTER(result);
}
/*
* redo any page update (except page split)
*/
static void
gistRedoPageUpdateRecord(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
gistxlogPageUpdate *xldata = (gistxlogPageUpdate *) XLogRecGetData(record);
Buffer buffer;
Page page;
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
char *begin;
char *data;
Size datalen;
int ninserted = 0;
data = begin = XLogRecGetBlockData(record, 0, &datalen);
page = (Page) BufferGetPage(buffer);
if (xldata->ntodelete == 1 && xldata->ntoinsert == 1)
{
/*
* When replacing one tuple with one other tuple, we must use
* PageIndexTupleOverwrite for consistency with gistplacetopage.
*/
OffsetNumber offnum = *((OffsetNumber *) data);
IndexTuple itup;
Size itupsize;
data += sizeof(OffsetNumber);
itup = (IndexTuple) data;
itupsize = IndexTupleSize(itup);
if (!PageIndexTupleOverwrite(page, offnum, (Item) itup, itupsize))
elog(ERROR, "failed to add item to GiST index page, size %d bytes",
(int) itupsize);
data += itupsize;
/* should be nothing left after consuming 1 tuple */
Assert(data - begin == datalen);
/* update insertion count for assert check below */
ninserted++;
}
else if (xldata->ntodelete > 0)
{
/* Otherwise, delete old tuples if any */
OffsetNumber *todelete = (OffsetNumber *) data;
data += sizeof(OffsetNumber) * xldata->ntodelete;
PageIndexMultiDelete(page, todelete, xldata->ntodelete);
if (GistPageIsLeaf(page))
GistMarkTuplesDeleted(page);
}
/* Add new tuples if any */
if (data - begin < datalen)
{
OffsetNumber off = (PageIsEmpty(page)) ? FirstOffsetNumber :
OffsetNumberNext(PageGetMaxOffsetNumber(page));
while (data - begin < datalen)
{
IndexTuple itup = (IndexTuple) data;
Size sz = IndexTupleSize(itup);
OffsetNumber l;
data += sz;
l = PageAddItem(page, (Item) itup, sz, off, false, false);
if (l == InvalidOffsetNumber)
elog(ERROR, "failed to add item to GiST index page, size %d bytes",
(int) sz);
off++;
ninserted++;
}
}
/* Check that XLOG record contained expected number of tuples */
Assert(ninserted == xldata->ntoinsert);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
/*
* Fix follow-right data on left child page
*
* This must be done while still holding the lock on the target page. Note
* that even if the target page no longer exists, we still attempt to
* replay the change on the child page.
*/
if (XLogRecHasBlockRef(record, 1))
gistRedoClearFollowRight(record, 1);
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
static void
gistRedoPageSplitRecord(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
Buffer firstbuffer = InvalidBuffer;
Buffer buffer;
Page page;
int i;
bool isrootsplit = false;
/*
* We must hold lock on the first-listed page throughout the action,
* including while updating the left child page (if any). We can unlock
* remaining pages in the list as soon as they've been written, because
* there is no path for concurrent queries to reach those pages without
* first visiting the first-listed page.
*/
/* loop around all pages */
for (i = 0; i < xldata->npage; i++)
{
int flags;
char *data;
Size datalen;
int num;
BlockNumber blkno;
IndexTuple *tuples;
XLogRecGetBlockTag(record, i + 1, NULL, NULL, &blkno);
if (blkno == GIST_ROOT_BLKNO)
{
Assert(i == 0);
isrootsplit = true;
}
buffer = XLogInitBufferForRedo(record, i + 1);
page = (Page) BufferGetPage(buffer);
data = XLogRecGetBlockData(record, i + 1, &datalen);
tuples = decodePageSplitRecord(data, datalen, &num);
/* ok, clear buffer */
if (xldata->origleaf && blkno != GIST_ROOT_BLKNO)
flags = F_LEAF;
else
flags = 0;
GISTInitBuffer(buffer, flags);
/* and fill it */
gistfillbuffer(page, tuples, num, FirstOffsetNumber);
if (blkno == GIST_ROOT_BLKNO)
{
GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
GistPageSetNSN(page, xldata->orignsn);
GistClearFollowRight(page);
}
else
{
if (i < xldata->npage - 1)
{
BlockNumber nextblkno;
XLogRecGetBlockTag(record, i + 2, NULL, NULL, &nextblkno);
GistPageGetOpaque(page)->rightlink = nextblkno;
}
else
GistPageGetOpaque(page)->rightlink = xldata->origrlink;
GistPageSetNSN(page, xldata->orignsn);
if (i < xldata->npage - 1 && !isrootsplit &&
xldata->markfollowright)
GistMarkFollowRight(page);
else
GistClearFollowRight(page);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
if (i == 0)
firstbuffer = buffer;
else
UnlockReleaseBuffer(buffer);
}
/* Fix follow-right data on left child page, if any */
if (XLogRecHasBlockRef(record, 0))
gistRedoClearFollowRight(record, 0);
/* Finally, release lock on the first page */
UnlockReleaseBuffer(firstbuffer);
}
/*
* visibilitymap_truncate - truncate the visibility map
*
* The caller must hold AccessExclusiveLock on the relation, to ensure that
* other backends receive the smgr invalidation event that this function sends
* before they access the VM again.
*
* nheapblocks is the new size of the heap.
*/
void
visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
{
BlockNumber newnblocks;
/* last remaining block, byte, and bit */
BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks);
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
RelationOpenSmgr(rel);
/*
* If no visibility map has been created yet for this relation, there's
* nothing to truncate.
*/
if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
return;
/*
* Unless the new size is exactly at a visibility map page boundary, the
* tail bits in the last remaining map page, representing truncated heap
* blocks, need to be cleared. This is not only tidy, but also necessary
* because we don't get a chance to clear the bits if the heap is extended
* again.
*/
if (truncByte != 0 || truncBit != 0)
{
Buffer mapBuffer;
Page page;
char *map;
newnblocks = truncBlock + 1;
mapBuffer = vm_readbuf(rel, truncBlock, false);
if (!BufferIsValid(mapBuffer))
{
/* nothing to do, the file was already smaller */
return;
}
page = BufferGetPage(mapBuffer);
map = PageGetContents(page);
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
/* Clear out the unwanted bytes. */
MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
/*
* Mask out the unwanted bits of the last remaining byte.
*
* ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) -
* 1) = 00111111 ((1 << 7) - 1) = 01111111
*/
map[truncByte] &= (1 << truncBit) - 1;
MarkBufferDirty(mapBuffer);
UnlockReleaseBuffer(mapBuffer);
}
else
newnblocks = truncBlock;
if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) <= newnblocks)
{
/* nothing to do, the file was already smaller than requested size */
return;
}
/* Truncate the unused VM pages, and send smgr inval message */
smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks);
/*
* We might as well update the local smgr_vm_nblocks setting. smgrtruncate
* sent an smgr cache inval message, which will cause other backends to
* invalidate their copy of smgr_vm_nblocks, and this one too at the next
* command boundary. But this ensures it isn't outright wrong until then.
*/
if (rel->rd_smgr)
rel->rd_smgr->smgr_vm_nblocks = newnblocks;
}
/*
* _bt_getroot() -- Get the root page of the btree.
*
* Since the root page can move around the btree file, we have to read
* its location from the metadata page, and then read the root page
* itself. If no root page exists yet, we have to create one. The
* standard class of race conditions exists here; I think I covered
* them all in the Hopi Indian rain dance of lock requests below.
*
* The access type parameter (BT_READ or BT_WRITE) controls whether
* a new root page will be created or not. If access = BT_READ,
* and no root page exists, we just return InvalidBuffer. For
* BT_WRITE, we try to create the root page if it doesn't exist.
* NOTE that the returned root page will have only a read lock set
* on it even if access = BT_WRITE!
*
* The returned page is not necessarily the true root --- it could be
* a "fast root" (a page that is alone in its level due to deletions).
* Also, if the root page is split while we are "in flight" to it,
* what we will return is the old root, which is now just the leftmost
* page on a probably-not-very-wide level. For most purposes this is
* as good as or better than the true root, so we do not bother to
* insist on finding the true root. We do, however, guarantee to
* return a live (not deleted or half-dead) page.
*
* On successful return, the root page is pinned and read-locked.
* The metadata page is not locked or pinned on exit.
*/
Buffer
_bt_getroot(Relation rel, int access)
{
Buffer metabuf;
Page metapg;
BTPageOpaque metaopaque;
Buffer rootbuf;
Page rootpage;
BTPageOpaque rootopaque;
BlockNumber rootblkno;
uint32 rootlevel;
BTMetaPageData *metad;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
/*
* Try to use previously-cached metapage data to find the root. This
* normally saves one buffer access per index search, which is a very
* helpful savings in bufmgr traffic and hence contention.
*/
if (rel->rd_amcache != NULL)
{
metad = (BTMetaPageData *) rel->rd_amcache;
/* We shouldn't have cached it if any of these fail */
Assert(metad->btm_magic == BTREE_MAGIC);
Assert(metad->btm_version == BTREE_VERSION);
Assert(metad->btm_root != P_NONE);
rootblkno = metad->btm_fastroot;
Assert(rootblkno != P_NONE);
rootlevel = metad->btm_fastlevel;
rootbuf = _bt_getbuf(rel, rootblkno, BT_READ);
rootpage = BufferGetPage(rootbuf);
rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
/*
* Since the cache might be stale, we check the page more carefully
* here than normal. We *must* check that it's not deleted. If it's
* not alone on its level, then we reject too --- this may be overly
* paranoid but better safe than sorry. Note we don't check P_ISROOT,
* because that's not set in a "fast root".
*/
if (!P_IGNORE(rootopaque) &&
rootopaque->btpo.level == rootlevel &&
P_LEFTMOST(rootopaque) &&
P_RIGHTMOST(rootopaque))
{
/* OK, accept cached page as the root */
return rootbuf;
}
_bt_relbuf(rel, rootbuf);
/* Cache is stale, throw it away */
if (rel->rd_amcache)
pfree(rel->rd_amcache);
rel->rd_amcache = NULL;
}
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_READ);
metapg = BufferGetPage(metabuf);
metaopaque = (BTPageOpaque) PageGetSpecialPointer(metapg);
metad = BTPageGetMeta(metapg);
/* sanity-check the metapage */
if (!(metaopaque->btpo_flags & BTP_META) ||
metad->btm_magic != BTREE_MAGIC)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" is not a btree",
RelationGetRelationName(rel))));
if (metad->btm_version != BTREE_VERSION)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("version mismatch in index \"%s\": file version %d, code version %d",
RelationGetRelationName(rel),
metad->btm_version, BTREE_VERSION)));
/* if no root page initialized yet, do it */
if (metad->btm_root == P_NONE)
{
/* If access = BT_READ, caller doesn't want us to create root yet */
if (access == BT_READ)
{
_bt_relbuf(rel, metabuf);
return InvalidBuffer;
}
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
/* trade in our read lock for a write lock */
LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
LockBuffer(metabuf, BT_WRITE);
/*
* Race condition: if someone else initialized the metadata between
* the time we released the read lock and acquired the write lock, we
* must avoid doing it again.
*/
if (metad->btm_root != P_NONE)
{
/*
* Metadata initialized by someone else. In order to guarantee no
* deadlocks, we have to release the metadata page and start all
* over again. (Is that really true? But it's hardly worth trying
* to optimize this case.)
*/
_bt_relbuf(rel, metabuf);
return _bt_getroot(rel, access);
}
/*
* Get, initialize, write, and leave a lock of the appropriate type on
* the new root page. Since this is the first page in the tree, it's
* a leaf as well as the root.
*/
rootbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
rootblkno = BufferGetBlockNumber(rootbuf);
rootpage = BufferGetPage(rootbuf);
rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
rootopaque->btpo_prev = rootopaque->btpo_next = P_NONE;
rootopaque->btpo_flags = (BTP_LEAF | BTP_ROOT);
rootopaque->btpo.level = 0;
rootopaque->btpo_cycleid = 0;
/* NO ELOG(ERROR) till meta is updated */
START_CRIT_SECTION();
metad->btm_root = rootblkno;
metad->btm_level = 0;
metad->btm_fastroot = rootblkno;
metad->btm_fastlevel = 0;
MarkBufferDirty(rootbuf);
MarkBufferDirty(metabuf);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_newroot xlrec;
XLogRecPtr recptr;
XLogRecData rdata;
xl_btreenode_set(&(xlrec.btreenode), rel);
xlrec.rootblk = rootblkno;
xlrec.level = 0;
rdata.data = (char *) &xlrec;
rdata.len = SizeOfBtreeNewroot;
rdata.buffer = InvalidBuffer;
rdata.next = NULL;
recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT, &rdata);
PageSetLSN(rootpage, recptr);
PageSetTLI(rootpage, ThisTimeLineID);
PageSetLSN(metapg, recptr);
PageSetTLI(metapg, ThisTimeLineID);
}
END_CRIT_SECTION();
/*
* Send out relcache inval for metapage change (probably unnecessary
* here, but let's be safe).
*/
CacheInvalidateRelcache(rel);
/*
* swap root write lock for read lock. There is no danger of anyone
* else accessing the new root page while it's unlocked, since no one
* else knows where it is yet.
*/
LockBuffer(rootbuf, BUFFER_LOCK_UNLOCK);
LockBuffer(rootbuf, BT_READ);
/* okay, metadata is correct, release lock on it */
_bt_relbuf(rel, metabuf);
}
else
{
rootblkno = metad->btm_fastroot;
Assert(rootblkno != P_NONE);
rootlevel = metad->btm_fastlevel;
/*
* Cache the metapage data for next time
*/
rel->rd_amcache = MemoryContextAlloc(rel->rd_indexcxt,
sizeof(BTMetaPageData));
memcpy(rel->rd_amcache, metad, sizeof(BTMetaPageData));
/*
* We are done with the metapage; arrange to release it via first
* _bt_relandgetbuf call
*/
rootbuf = metabuf;
for (;;)
{
rootbuf = _bt_relandgetbuf(rel, rootbuf, rootblkno, BT_READ);
rootpage = BufferGetPage(rootbuf);
rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
if (!P_IGNORE(rootopaque))
break;
/* it's dead, Jim. step right one page */
if (P_RIGHTMOST(rootopaque))
elog(ERROR, "no live root page found in index \"%s\"",
RelationGetRelationName(rel));
rootblkno = rootopaque->btpo_next;
}
/* Note: can't check btpo.level on deleted pages */
if (rootopaque->btpo.level != rootlevel)
elog(ERROR, "root page %u of index \"%s\" has level %u, expected %u",
rootblkno, RelationGetRelationName(rel),
rootopaque->btpo.level, rootlevel);
}
/*
* By here, we have a pin and read lock on the root page, and no lock set
* on the metadata page. Return the root page's buffer.
*/
return rootbuf;
}
/*
* _bt_pagedel() -- Delete a page from the b-tree, if legal to do so.
*
* This action unlinks the page from the b-tree structure, removing all
* pointers leading to it --- but not touching its own left and right links.
* The page cannot be physically reclaimed right away, since other processes
* may currently be trying to follow links leading to the page; they have to
* be allowed to use its right-link to recover. See nbtree/README.
*
* On entry, the target buffer must be pinned and locked (either read or write
* lock is OK). This lock and pin will be dropped before exiting.
*
* The "stack" argument can be a search stack leading (approximately) to the
* target page, or NULL --- outside callers typically pass NULL since they
* have not done such a search, but internal recursion cases pass the stack
* to avoid duplicated search effort.
*
* Returns the number of pages successfully deleted (zero if page cannot
* be deleted now; could be more than one if parent pages were deleted too).
*
* NOTE: this leaks memory. Rather than trying to clean up everything
* carefully, it's better to run it in a temp context that can be reset
* frequently.
*/
int
_bt_pagedel(Relation rel, Buffer buf, BTStack stack, bool vacuum_full)
{
int result;
BlockNumber target,
leftsib,
rightsib,
parent;
OffsetNumber poffset,
maxoff;
uint32 targetlevel,
ilevel;
ItemId itemid;
IndexTuple targetkey,
itup;
ScanKey itup_scankey;
Buffer lbuf,
rbuf,
pbuf;
bool parent_half_dead;
bool parent_one_child;
bool rightsib_empty;
Buffer metabuf = InvalidBuffer;
Page metapg = NULL;
BTMetaPageData *metad = NULL;
Page page;
BTPageOpaque opaque;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
/*
* We can never delete rightmost pages nor root pages. While at it, check
* that page is not already deleted and is empty.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
/* Should never fail to delete a half-dead page */
Assert(!P_ISHALFDEAD(opaque));
_bt_relbuf(rel, buf);
return 0;
}
/*
* Save info about page, including a copy of its high key (it must have
* one, being non-rightmost).
*/
target = BufferGetBlockNumber(buf);
targetlevel = opaque->btpo.level;
leftsib = opaque->btpo_prev;
itemid = PageGetItemId(page, P_HIKEY);
targetkey = CopyIndexTuple((IndexTuple) PageGetItem(page, itemid));
/*
* To avoid deadlocks, we'd better drop the target page lock before going
* further.
*/
_bt_relbuf(rel, buf);
/*
* We need an approximate pointer to the page's parent page. We use the
* standard search mechanism to search for the page's high key; this will
* give us a link to either the current parent or someplace to its left
* (if there are multiple equal high keys). In recursion cases, the
* caller already generated a search stack and we can just re-use that
* work.
*/
if (stack == NULL)
{
if (!InRecovery)
{
/* we need an insertion scan key to do our search, so build one */
itup_scankey = _bt_mkscankey(rel, targetkey);
/* find the leftmost leaf page containing this key */
stack = _bt_search(rel, rel->rd_rel->relnatts, itup_scankey, false,
&lbuf, BT_READ);
/* don't need a pin on that either */
_bt_relbuf(rel, lbuf);
/*
* If we are trying to delete an interior page, _bt_search did
* more than we needed. Locate the stack item pointing to our
* parent level.
*/
ilevel = 0;
for (;;)
{
if (stack == NULL)
elog(ERROR, "not enough stack items");
if (ilevel == targetlevel)
break;
stack = stack->bts_parent;
ilevel++;
}
}
else
{
/*
* During WAL recovery, we can't use _bt_search (for one reason,
* it might invoke user-defined comparison functions that expect
* facilities not available in recovery mode). Instead, just set
* up a dummy stack pointing to the left end of the parent tree
* level, from which _bt_getstackbuf will walk right to the parent
* page. Painful, but we don't care too much about performance in
* this scenario.
*/
pbuf = _bt_get_endpoint(rel, targetlevel + 1, false);
stack = (BTStack) palloc(sizeof(BTStackData));
stack->bts_blkno = BufferGetBlockNumber(pbuf);
stack->bts_offset = InvalidOffsetNumber;
/* bts_btentry will be initialized below */
stack->bts_parent = NULL;
_bt_relbuf(rel, pbuf);
}
}
/*
* We cannot delete a page that is the rightmost child of its immediate
* parent, unless it is the only child --- in which case the parent has to
* be deleted too, and the same condition applies recursively to it. We
* have to check this condition all the way up before trying to delete. We
* don't need to re-test when deleting a non-leaf page, though.
*/
if (targetlevel == 0 &&
!_bt_parent_deletion_safe(rel, target, stack))
return 0;
/*
* We have to lock the pages we need to modify in the standard order:
* moving right, then up. Else we will deadlock against other writers.
*
* So, we need to find and write-lock the current left sibling of the
* target page. The sibling that was current a moment ago could have
* split, so we may have to move right. This search could fail if either
* the sibling or the target page was deleted by someone else meanwhile;
* if so, give up. (Right now, that should never happen, since page
* deletion is only done in VACUUM and there shouldn't be multiple VACUUMs
* concurrently on the same table.)
*/
if (leftsib != P_NONE)
{
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
while (P_ISDELETED(opaque) || opaque->btpo_next != target)
{
/* step right one page */
leftsib = opaque->btpo_next;
_bt_relbuf(rel, lbuf);
if (leftsib == P_NONE)
{
elog(LOG, "no left sibling (concurrent deletion?) in \"%s\"",
RelationGetRelationName(rel));
return 0;
}
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
}
else
lbuf = InvalidBuffer;
/*
* Next write-lock the target page itself. It should be okay to take just
* a write lock not a superexclusive lock, since no scans would stop on an
* empty page.
*/
buf = _bt_getbuf(rel, target, BT_WRITE);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* Check page is still empty etc, else abandon deletion. The empty check
* is necessary since someone else might have inserted into it while we
* didn't have it locked; the others are just for paranoia's sake.
*/
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
if (opaque->btpo_prev != leftsib)
elog(ERROR, "left link changed unexpectedly in block %u of index \"%s\"",
target, RelationGetRelationName(rel));
/*
* And next write-lock the (current) right sibling.
*/
rightsib = opaque->btpo_next;
rbuf = _bt_getbuf(rel, rightsib, BT_WRITE);
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (opaque->btpo_prev != target)
elog(ERROR, "right sibling's left-link doesn't match: "
"block %u links to %u instead of expected %u in index \"%s\"",
rightsib, opaque->btpo_prev, target,
RelationGetRelationName(rel));
/*
* Next find and write-lock the current parent of the target page. This is
* essentially the same as the corresponding step of splitting.
*/
ItemPointerSet(&(stack->bts_btentry.t_tid), target, P_HIKEY);
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
elog(ERROR, "failed to re-find parent key in index \"%s\" for deletion target page %u",
RelationGetRelationName(rel), target);
parent = stack->bts_blkno;
poffset = stack->bts_offset;
/*
* If the target is the rightmost child of its parent, then we can't
* delete, unless it's also the only child --- in which case the parent
* changes to half-dead status. The "can't delete" case should have been
* detected by _bt_parent_deletion_safe, so complain if we see it now.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
maxoff = PageGetMaxOffsetNumber(page);
parent_half_dead = false;
parent_one_child = false;
if (poffset >= maxoff)
{
if (poffset == P_FIRSTDATAKEY(opaque))
parent_half_dead = true;
else
elog(ERROR, "failed to delete rightmost child %u of block %u in index \"%s\"",
target, parent, RelationGetRelationName(rel));
}
else
{
/* Will there be exactly one child left in this parent? */
if (OffsetNumberNext(P_FIRSTDATAKEY(opaque)) == maxoff)
parent_one_child = true;
}
/*
* If we are deleting the next-to-last page on the target's level, then
* the rightsib is a candidate to become the new fast root. (In theory, it
* might be possible to push the fast root even further down, but the odds
* of doing so are slim, and the locking considerations daunting.)
*
* We don't support handling this in the case where the parent is becoming
* half-dead, even though it theoretically could occur.
*
* We can safely acquire a lock on the metapage here --- see comments for
* _bt_newroot().
*/
if (leftsib == P_NONE && !parent_half_dead)
{
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo.level == targetlevel);
if (P_RIGHTMOST(opaque))
{
/* rightsib will be the only one left on the level */
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_WRITE);
metapg = BufferGetPage(metabuf);
metad = BTPageGetMeta(metapg);
/*
* The expected case here is btm_fastlevel == targetlevel+1; if
* the fastlevel is <= targetlevel, something is wrong, and we
* choose to overwrite it to fix it.
*/
if (metad->btm_fastlevel > targetlevel + 1)
{
/* no update wanted */
_bt_relbuf(rel, metabuf);
metabuf = InvalidBuffer;
}
}
}
/*
* Check that the parent-page index items we're about to delete/overwrite
* contain what we expect. This can fail if the index has become
* corrupt for some reason. We want to throw any error before entering
* the critical section --- otherwise it'd be a PANIC.
*
* The test on the target item is just an Assert because _bt_getstackbuf
* should have guaranteed it has the expected contents. The test on the
* next-child downlink is known to sometimes fail in the field, though.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
#ifdef USE_ASSERT_CHECKING
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
Assert(ItemPointerGetBlockNumber(&(itup->t_tid)) == target);
#endif
if (!parent_half_dead)
{
OffsetNumber nextoffset;
nextoffset = OffsetNumberNext(poffset);
itemid = PageGetItemId(page, nextoffset);
itup = (IndexTuple) PageGetItem(page, itemid);
if (ItemPointerGetBlockNumber(&(itup->t_tid)) != rightsib)
elog(ERROR, "right sibling %u of block %u is not next child %u of block %u in index \"%s\"",
rightsib, target, ItemPointerGetBlockNumber(&(itup->t_tid)),
parent, RelationGetRelationName(rel));
}
/*
* Here we begin doing the deletion.
*/
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/*
* Update parent. The normal case is a tad tricky because we want to
* delete the target's downlink and the *following* key. Easiest way is
* to copy the right sibling's downlink over the target downlink, and then
* delete the following item.
*/
if (parent_half_dead)
{
PageIndexTupleDelete(page, poffset);
opaque->btpo_flags |= BTP_HALF_DEAD;
}
else
{
OffsetNumber nextoffset;
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
PageIndexTupleDelete(page, nextoffset);
}
/*
* Update siblings' side-links. Note the target page's side-links will
* continue to point to the siblings. Asserts here are just rechecking
* things we already verified above.
*/
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_next == target);
opaque->btpo_next = rightsib;
}
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_prev == target);
opaque->btpo_prev = leftsib;
rightsib_empty = (P_FIRSTDATAKEY(opaque) > PageGetMaxOffsetNumber(page));
/*
* Mark the page itself deleted. It can be recycled when all current
* transactions are gone; or immediately if we're doing VACUUM FULL.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags &= ~BTP_HALF_DEAD;
opaque->btpo_flags |= BTP_DELETED;
opaque->btpo.xact =
vacuum_full ? FrozenTransactionId : ReadNewTransactionId();
/* And update the metapage, if needed */
if (BufferIsValid(metabuf))
{
metad->btm_fastroot = rightsib;
metad->btm_fastlevel = targetlevel;
MarkBufferDirty(metabuf);
}
/* Must mark buffers dirty before XLogInsert */
MarkBufferDirty(pbuf);
MarkBufferDirty(rbuf);
MarkBufferDirty(buf);
if (BufferIsValid(lbuf))
MarkBufferDirty(lbuf);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete_page xlrec;
xl_btree_metadata xlmeta;
uint8 xlinfo;
XLogRecPtr recptr;
XLogRecData rdata[5];
XLogRecData *nextrdata;
xl_btreetid_set(&(xlrec.target), rel, parent, poffset);
xlrec.deadblk = target;
xlrec.leftblk = leftsib;
xlrec.rightblk = rightsib;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeDeletePage;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = nextrdata = &(rdata[1]);
if (BufferIsValid(metabuf))
{
xlmeta.root = metad->btm_root;
xlmeta.level = metad->btm_level;
xlmeta.fastroot = metad->btm_fastroot;
xlmeta.fastlevel = metad->btm_fastlevel;
nextrdata->data = (char *) &xlmeta;
nextrdata->len = sizeof(xl_btree_metadata);
nextrdata->buffer = InvalidBuffer;
nextrdata->next = nextrdata + 1;
nextrdata++;
xlinfo = XLOG_BTREE_DELETE_PAGE_META;
}
else if (parent_half_dead)
xlinfo = XLOG_BTREE_DELETE_PAGE_HALF;
else
xlinfo = XLOG_BTREE_DELETE_PAGE;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->next = nextrdata + 1;
nextrdata->buffer = pbuf;
nextrdata->buffer_std = true;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = rbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
if (BufferIsValid(lbuf))
{
nextrdata->next = nextrdata + 1;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = lbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
}
recptr = XLogInsert(RM_BTREE_ID, xlinfo, rdata);
if (BufferIsValid(metabuf))
{
PageSetLSN(metapg, recptr);
PageSetTLI(metapg, ThisTimeLineID);
}
page = BufferGetPage(pbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(rbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(buf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
END_CRIT_SECTION();
/* release metapage; send out relcache inval if metapage changed */
if (BufferIsValid(metabuf))
{
CacheInvalidateRelcache(rel);
_bt_relbuf(rel, metabuf);
}
/* can always release leftsib immediately */
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
/*
* If parent became half dead, recurse to delete it. Otherwise, if right
* sibling is empty and is now the last child of the parent, recurse to
* try to delete it. (These cases cannot apply at the same time, though
* the second case might itself recurse to the first.)
*
* When recursing to parent, we hold the lock on the target page until
* done. This delays any insertions into the keyspace that was just
* effectively reassigned to the parent's right sibling. If we allowed
* that, and there were enough such insertions before we finish deleting
* the parent, page splits within that keyspace could lead to inserting
* out-of-order keys into the grandparent level. It is thought that that
* wouldn't have any serious consequences, but it still seems like a
* pretty bad idea.
*/
if (parent_half_dead)
{
/* recursive call will release pbuf */
_bt_relbuf(rel, rbuf);
result = _bt_pagedel(rel, pbuf, stack->bts_parent, vacuum_full) + 1;
_bt_relbuf(rel, buf);
}
else if (parent_one_child && rightsib_empty)
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
/* recursive call will release rbuf */
result = _bt_pagedel(rel, rbuf, stack, vacuum_full) + 1;
}
else
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
_bt_relbuf(rel, rbuf);
result = 1;
}
return result;
}
/*
* Delete item(s) from a btree page.
*
* This must only be used for deleting leaf items. Deleting an item on a
* non-leaf page has to be done as part of an atomic action that includes
* deleting the page it points to.
*
* This routine assumes that the caller has pinned and locked the buffer.
* Also, the given itemnos *must* appear in increasing order in the array.
*/
void
_bt_delitems(Relation rel, Buffer buf,
OffsetNumber *itemnos, int nitems,
bool inVacuum)
{
Page page;
BTPageOpaque opaque;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
page = BufferGetPage(buf);
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/* Fix the page */
PageIndexMultiDelete(page, itemnos, nitems);
/*
* If this is within VACUUM, we can clear the vacuum cycle ID since this
* page has certainly been processed by the current vacuum scan.
*/
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (inVacuum)
opaque->btpo_cycleid = 0;
/*
* Mark the page as not containing any LP_DEAD items. This is not
* certainly true (there might be some that have recently been marked, but
* weren't included in our target-item list), but it will almost always be
* true and it doesn't seem worth an additional page scan to check it.
* Remember that BTP_HAS_GARBAGE is only a hint anyway.
*/
opaque->btpo_flags &= ~BTP_HAS_GARBAGE;
MarkBufferDirty(buf);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete xlrec;
XLogRecPtr recptr;
XLogRecData rdata[2];
xl_btreenode_set(&(xlrec.btreenode), rel);
xlrec.block = BufferGetBlockNumber(buf);
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeDelete;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = &(rdata[1]);
/*
* The target-offsets array is not in the buffer, but pretend that it
* is. When XLogInsert stores the whole buffer, the offsets array
* need not be stored too.
*/
if (nitems > 0)
{
rdata[1].data = (char *) itemnos;
rdata[1].len = nitems * sizeof(OffsetNumber);
}
else
{
rdata[1].data = NULL;
rdata[1].len = 0;
}
rdata[1].buffer = buf;
rdata[1].buffer_std = true;
rdata[1].next = NULL;
recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_DELETE, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
END_CRIT_SECTION();
}
Datum
ginbulkdelete(PG_FUNCTION_ARGS)
{
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
IndexBulkDeleteCallback callback = (IndexBulkDeleteCallback) PG_GETARG_POINTER(2);
void *callback_state = (void *) PG_GETARG_POINTER(3);
Relation index = info->index;
BlockNumber blkno = GIN_ROOT_BLKNO;
GinVacuumState gvs;
Buffer buffer;
BlockNumber rootOfPostingTree[BLCKSZ / (sizeof(IndexTupleData) + sizeof(ItemId))];
uint32 nRoot;
gvs.index = index;
gvs.callback = callback;
gvs.callback_state = callback_state;
gvs.strategy = info->strategy;
initGinState(&gvs.ginstate, index);
/* first time through? */
if (stats == NULL)
{
/* Yes, so initialize stats to zeroes */
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
/* and cleanup any pending inserts */
ginInsertCleanup(&gvs.ginstate, true, stats);
}
/* we'll re-count the tuples each time */
stats->num_index_tuples = 0;
gvs.result = stats;
buffer = ReadBufferExtended(index, MAIN_FORKNUM, blkno,
RBM_NORMAL, info->strategy);
/* find leaf page */
for (;;)
{
Page page = BufferGetPage(buffer);
IndexTuple itup;
LockBuffer(buffer, GIN_SHARE);
Assert(!GinPageIsData(page));
if (GinPageIsLeaf(page))
{
LockBuffer(buffer, GIN_UNLOCK);
LockBuffer(buffer, GIN_EXCLUSIVE);
if (blkno == GIN_ROOT_BLKNO && !GinPageIsLeaf(page))
{
LockBuffer(buffer, GIN_UNLOCK);
continue; /* check it one more */
}
break;
}
Assert(PageGetMaxOffsetNumber(page) >= FirstOffsetNumber);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, FirstOffsetNumber));
blkno = GinGetDownlink(itup);
Assert(blkno != InvalidBlockNumber);
UnlockReleaseBuffer(buffer);
buffer = ReadBufferExtended(index, MAIN_FORKNUM, blkno,
RBM_NORMAL, info->strategy);
}
/* right now we found leftmost page in entry's BTree */
for (;;)
{
Page page = BufferGetPage(buffer);
Page resPage;
uint32 i;
Assert(!GinPageIsData(page));
resPage = ginVacuumEntryPage(&gvs, buffer, rootOfPostingTree, &nRoot);
blkno = GinPageGetOpaque(page)->rightlink;
if (resPage)
{
START_CRIT_SECTION();
PageRestoreTempPage(resPage, page);
MarkBufferDirty(buffer);
xlogVacuumPage(gvs.index, buffer);
UnlockReleaseBuffer(buffer);
END_CRIT_SECTION();
}
else
{
UnlockReleaseBuffer(buffer);
}
vacuum_delay_point();
for (i = 0; i < nRoot; i++)
{
ginVacuumPostingTree(&gvs, rootOfPostingTree[i]);
vacuum_delay_point();
}
if (blkno == InvalidBlockNumber) /* rightmost page */
break;
buffer = ReadBufferExtended(index, MAIN_FORKNUM, blkno,
RBM_NORMAL, info->strategy);
LockBuffer(buffer, GIN_EXCLUSIVE);
}
PG_RETURN_POINTER(gvs.result);
}