static void
spgRedoCreateIndex(XLogRecPtr lsn, XLogRecord *record)
{
RelFileNode *node = (RelFileNode *) XLogRecGetData(record);
Buffer buffer;
Page page;
buffer = XLogReadBuffer(*node, SPGIST_METAPAGE_BLKNO, true);
Assert(BufferIsValid(buffer));
page = (Page) BufferGetPage(buffer);
SpGistInitMetapage(page);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
buffer = XLogReadBuffer(*node, SPGIST_HEAD_BLKNO, true);
Assert(BufferIsValid(buffer));
SpGistInitBuffer(buffer, SPGIST_LEAF);
page = (Page) BufferGetPage(buffer);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/*
* _bitmap_log_bitmap_lastwords() -- log the last two words in a bitmap.
*/
void
_bitmap_log_bitmap_lastwords(Relation rel, Buffer lovBuffer,
OffsetNumber lovOffset, BMLOVItem lovItem)
{
xl_bm_bitmap_lastwords xlLastwords;
XLogRecPtr recptr;
XLogRecData rdata[1];
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
xlLastwords.bm_node = rel->rd_node;
xlLastwords.bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlLastwords.bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlLastwords.bm_last_compword = lovItem->bm_last_compword;
xlLastwords.bm_last_word = lovItem->bm_last_word;
xlLastwords.lov_words_header = lovItem->lov_words_header;
xlLastwords.bm_last_setbit = lovItem->bm_last_setbit;
xlLastwords.bm_last_tid_location = lovItem->bm_last_tid_location;
xlLastwords.bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlLastwords.bm_lov_offset = lovOffset;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlLastwords;
rdata[0].len = sizeof(xl_bm_bitmap_lastwords);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_INSERT_BITMAP_LASTWORDS,
rdata);
PageSetLSN(BufferGetPage(lovBuffer), recptr);
PageSetTLI(BufferGetPage(lovBuffer), ThisTimeLineID);
}
/*
* _bitmap_log_metapage() -- log the changes to the metapage
*/
void
_bitmap_log_metapage(Relation rel, BMMetaPage metapage)
{
/* XLOG stuff */
START_CRIT_SECTION();
if (!(rel->rd_istemp))
{
xl_bm_metapage* xlMeta;
XLogRecPtr recptr;
XLogRecData rdata[1];
#ifdef BM_DEBUG
elog(LOG, "call _bitmap_log_metapage.");
#endif
xlMeta = (xl_bm_metapage*)
palloc(MAXALIGN(sizeof(xl_bm_metapage)));
xlMeta->bm_node = rel->rd_node;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)xlMeta;
rdata[0].len = MAXALIGN(sizeof(xl_bm_metapage));
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_INSERT_META, rdata);
PageSetLSN(metapage, recptr);
PageSetTLI(metapage, ThisTimeLineID);
pfree(xlMeta);
}
END_CRIT_SECTION();
}
/*
* Replay the clearing of F_FOLLOW_RIGHT flag.
*/
static void
gistRedoClearFollowRight(RelFileNode node, XLogRecPtr lsn,
BlockNumber leftblkno)
{
Buffer buffer;
buffer = XLogReadBuffer(node, leftblkno, false);
if (BufferIsValid(buffer))
{
Page page = (Page) BufferGetPage(buffer);
/*
* Note that we still update the page even if page LSN is equal to the
* LSN of this record, because the updated NSN is not included in the
* full page image.
*/
if (!XLByteLT(lsn, PageGetLSN(page)))
{
GistPageGetOpaque(page)->nsn = lsn;
GistClearFollowRight(page);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/*
* Replay the clearing of F_FOLLOW_RIGHT flag on a child page.
*
* Even if the WAL record includes a full-page image, we have to update the
* follow-right flag, because that change is not included in the full-page
* image. To be sure that the intermediate state with the wrong flag value is
* not visible to concurrent Hot Standby queries, this function handles
* restoring the full-page image as well as updating the flag. (Note that
* we never need to do anything else to the child page in the current WAL
* action.)
*/
static void
gistRedoClearFollowRight(XLogRecPtr lsn, XLogRecord *record, int block_index,
RelFileNode node, BlockNumber childblkno)
{
Buffer buffer;
Page page;
if (record->xl_info & XLR_BKP_BLOCK(block_index))
buffer = RestoreBackupBlock(lsn, record, block_index, false, true);
else
{
buffer = XLogReadBuffer(node, childblkno, false);
if (!BufferIsValid(buffer))
return; /* page was deleted, nothing to do */
}
page = (Page) BufferGetPage(buffer);
/*
* Note that we still update the page even if page LSN is equal to the LSN
* of this record, because the updated NSN is not included in the full
* page image.
*/
if (lsn >= PageGetLSN(page))
{
GistPageSetNSN(page, lsn);
GistClearFollowRight(page);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the heap page. The LSN of the visibility map page is
* advanced to that, to make sure that the visibility map doesn't get flushed
* to disk before the update to the heap page that made all tuples visible.
*
* This is an opportunistic function. It does nothing, unless *buf
* contains the bit for heapBlk. Call visibilitymap_pin first to pin
* the right map page. This function doesn't do any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, XLogRecPtr recptr,
Buffer *buf)
{
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
/* Check that we have the right page pinned */
if (!BufferIsValid(*buf) || BufferGetBlockNumber(*buf) != mapBlock)
return;
page = BufferGetPage(*buf);
map = PageGetContents(page);
LockBuffer(*buf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
map[mapByte] |= (1 << mapBit);
if (XLByteLT(PageGetLSN(page), recptr))
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(*buf);
}
LockBuffer(*buf, BUFFER_LOCK_UNLOCK);
}
static void
spgRedoVacuumRoot(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogVacuumRoot *xldata = (spgxlogVacuumRoot *) ptr;
OffsetNumber *toDelete;
Buffer buffer;
Page page;
ptr += sizeof(spgxlogVacuumRoot);
toDelete = (OffsetNumber *) ptr;
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, SPGIST_HEAD_BLKNO, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
/* The tuple numbers are in order */
PageIndexMultiDelete(page, toDelete, xldata->nDelete);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
/*
* buffer must be pinned and locked by caller
*/
void
gistnewroot(Relation r, Buffer buffer, IndexTuple *itup, int len, ItemPointer key)
{
Page page;
Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
page = BufferGetPage(buffer);
START_CRIT_SECTION();
GISTInitBuffer(buffer, 0);
gistfillbuffer(r, page, itup, len, FirstOffsetNumber);
MarkBufferDirty(buffer);
if (!r->rd_istemp)
{
XLogRecPtr recptr;
XLogRecData *rdata;
rdata = formUpdateRdata(r, buffer,
NULL, 0,
itup, len, key);
recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_NEW_ROOT, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
else
PageSetLSN(page, XLogRecPtrForTemp);
END_CRIT_SECTION();
}
/*
* _bitmap_log_newpage() -- log a new page.
*
* This function is called before writing a new buffer.
*/
void
_bitmap_log_newpage(Relation rel, uint8 info, Buffer buf)
{
Page page;
xl_bm_newpage xlNewPage;
XLogRecPtr recptr;
XLogRecData rdata[1];
page = BufferGetPage(buf);
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
xlNewPage.bm_node = rel->rd_node;
xlNewPage.bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlNewPage.bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlNewPage.bm_new_blkno = BufferGetBlockNumber(buf);
elog(DEBUG1, "_bitmap_log_newpage: blkno=%d", xlNewPage.bm_new_blkno);
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *)&xlNewPage;
rdata[0].len = sizeof(xl_bm_newpage);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, info, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
/*
* _bitmap_log_metapage() -- log the changes to the metapage
*/
void
_bitmap_log_metapage(Relation rel, Page page)
{
BMMetaPage metapage = (BMMetaPage) PageGetContents(page);
xl_bm_metapage* xlMeta;
XLogRecPtr recptr;
XLogRecData rdata[1];
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
xlMeta = (xl_bm_metapage *)
palloc(MAXALIGN(sizeof(xl_bm_metapage)));
xlMeta->bm_node = rel->rd_node;
xlMeta->bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlMeta->bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlMeta->bm_lov_heapId = metapage->bm_lov_heapId;
xlMeta->bm_lov_indexId = metapage->bm_lov_indexId;
xlMeta->bm_lov_lastpage = metapage->bm_lov_lastpage;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)xlMeta;
rdata[0].len = MAXALIGN(sizeof(xl_bm_metapage));
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_INSERT_META, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
pfree(xlMeta);
}
/*
* _bt_lognewpage() -- create an XLOG entry for a new page of the btree.
*/
void
_bt_lognewpage(Relation index,
Page newPage,
BlockNumber blockNo)
{
/* We use the heap NEWPAGE record type for this */
xl_heap_newpage xlrec;
XLogRecPtr recptr;
XLogRecData rdata[2];
/* NO ELOG(ERROR) from here till newpage op is logged */
START_CRIT_SECTION();
xl_heapnode_set(&xlrec.heapnode, index);
xlrec.blkno = blockNo;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfHeapNewpage;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = &(rdata[1]);
rdata[1].data = (char *) newPage;
rdata[1].len = BLCKSZ;
rdata[1].buffer = InvalidBuffer;
rdata[1].next = NULL;
recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_NEWPAGE, rdata);
PageSetLSN(newPage, recptr);
PageSetTLI(newPage, ThisTimeLineID);
END_CRIT_SECTION();
}
/*
* _bitmap_log_lovitem() -- log adding a new lov item to a lov page.
*/
void
_bitmap_log_lovitem(Relation rel, Buffer lovBuffer, OffsetNumber offset,
BMLOVItem lovItem, Buffer metabuf, bool is_new_lov_blkno)
{
Page lovPage = BufferGetPage(lovBuffer);
xl_bm_lovitem xlLovItem;
XLogRecPtr recptr;
XLogRecData rdata[1];
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
Assert(BufferGetBlockNumber(lovBuffer) > 0);
xlLovItem.bm_node = rel->rd_node;
xlLovItem.bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlLovItem.bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlLovItem.bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlLovItem.bm_lov_offset = offset;
memcpy(&(xlLovItem.bm_lovItem), lovItem, sizeof(BMLOVItemData));
xlLovItem.bm_is_new_lov_blkno = is_new_lov_blkno;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlLovItem;
rdata[0].len = sizeof(xl_bm_lovitem);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID,
XLOG_BITMAP_INSERT_LOVITEM, rdata);
if (is_new_lov_blkno)
{
Page metapage = BufferGetPage(metabuf);
PageSetLSN(metapage, recptr);
PageSetTLI(metapage, ThisTimeLineID);
}
PageSetLSN(lovPage, recptr);
PageSetTLI(lovPage, ThisTimeLineID);
elog(DEBUG1, "Insert a new lovItem at (blockno, offset): (%d,%d)",
BufferGetBlockNumber(lovBuffer), offset);
}
/*
* emit a completed btree page, and release the working storage.
*/
static void
_bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
{
/* Ensure rd_smgr is open (could have been closed by relcache flush!) */
RelationOpenSmgr(wstate->index);
/* XLOG stuff */
if (wstate->btws_use_wal)
{
/* We use the heap NEWPAGE record type for this */
log_newpage(&wstate->index->rd_node, MAIN_FORKNUM, blkno, page);
}
else
{
/* Leave the page LSN zero if not WAL-logged, but set TLI anyway */
PageSetTLI(page, ThisTimeLineID);
}
/*
* If we have to write pages nonsequentially, fill in the space with
* zeroes until we come back and overwrite. This is not logically
* necessary on standard Unix filesystems (unwritten space will read as
* zeroes anyway), but it should help to avoid fragmentation. The dummy
* pages aren't WAL-logged though.
*/
while (blkno > wstate->btws_pages_written)
{
if (!wstate->btws_zeropage)
wstate->btws_zeropage = (Page) palloc0(BLCKSZ);
smgrextend(wstate->index->rd_smgr, MAIN_FORKNUM,
wstate->btws_pages_written++,
(char *) wstate->btws_zeropage,
true);
}
/*
* Now write the page. We say isTemp = true even if it's not a temp
* index, because there's no need for smgr to schedule an fsync for this
* write; we'll do it ourselves before ending the build.
*/
if (blkno == wstate->btws_pages_written)
{
/* extending the file... */
smgrextend(wstate->index->rd_smgr, MAIN_FORKNUM, blkno,
(char *) page, true);
wstate->btws_pages_written++;
}
else
{
/* overwriting a block we zero-filled before */
smgrwrite(wstate->index->rd_smgr, MAIN_FORKNUM, blkno,
(char *) page, true);
}
pfree(page);
}
/*
* 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,
* and will write the buffer afterwards. Also, the given itemnos *must*
* appear in increasing order in the array.
*/
void
_bt_delitems(Relation rel, Buffer buf,
OffsetNumber *itemnos, int nitems)
{
Page page = BufferGetPage(buf);
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/* Fix the page */
PageIndexMultiDelete(page, itemnos, nitems);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete xlrec;
XLogRecPtr recptr;
XLogRecData rdata[2];
xlrec.node = rel->rd_node;
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();
}
/*
* _bitmap_log_lovmetapage() -- log the lov meta page.
*/
void
_bitmap_log_lovmetapage(Relation rel, Buffer lovMetaBuffer, uint8 numOfAttrs)
{
Page lovMetapage;
BMLOVMetaItem metaItems;
lovMetapage = BufferGetPage(lovMetaBuffer);
metaItems = (BMLOVMetaItem)PageGetContents(lovMetapage);
/* XLOG stuff */
START_CRIT_SECTION();
if (!(rel->rd_istemp))
{
BMLOVMetaItem copyMetaItems;
XLogRecPtr recptr;
XLogRecData rdata[1];
xl_bm_lovmetapage* xlLovMeta;
#ifdef BM_DEBUG
elog(LOG, "call _bitmap_log_lovmetapage: numOfAttrs=%d", numOfAttrs);
#endif
xlLovMeta = (xl_bm_lovmetapage*)
palloc(sizeof(xl_bm_lovmetapage)+
numOfAttrs*sizeof(BMLOVMetaItemData));
xlLovMeta->bm_node = rel->rd_node;
xlLovMeta->bm_num_of_attrs = numOfAttrs;
copyMetaItems = (BMLOVMetaItem)
(((char*)xlLovMeta) + sizeof(xl_bm_lovmetapage));
memcpy(copyMetaItems, metaItems, numOfAttrs*sizeof(BMLOVMetaItemData));
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)xlLovMeta;
rdata[0].len =
sizeof(xl_bm_lovmetapage) + numOfAttrs*sizeof(BMLOVMetaItemData);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID,
XLOG_BITMAP_INSERT_LOVMETA, rdata);
PageSetLSN(lovMetapage, recptr);
PageSetTLI(lovMetapage, ThisTimeLineID);
pfree(xlLovMeta);
}
END_CRIT_SECTION();
}
/*
* Creates posting tree with one page. Function
* suppose that items[] fits to page
*/
static BlockNumber
createPostingTree(Relation index, ItemPointerData *items, uint32 nitems)
{
BlockNumber blkno;
Buffer buffer = GinNewBuffer(index);
Page page;
START_CRIT_SECTION();
GinInitBuffer(buffer, GIN_DATA | GIN_LEAF);
page = BufferGetPage(buffer);
blkno = BufferGetBlockNumber(buffer);
memcpy(GinDataPageGetData(page), items, sizeof(ItemPointerData) * nitems);
GinPageGetOpaque(page)->maxoff = nitems;
MarkBufferDirty(buffer);
if (!index->rd_istemp)
{
XLogRecPtr recptr;
XLogRecData rdata[2];
ginxlogCreatePostingTree data;
data.node = index->rd_node;
data.blkno = blkno;
data.nitem = nitems;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogCreatePostingTree);
rdata[0].next = &rdata[1];
rdata[1].buffer = InvalidBuffer;
rdata[1].data = (char *) items;
rdata[1].len = sizeof(ItemPointerData) * nitems;
rdata[1].next = NULL;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_PTREE, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
UnlockReleaseBuffer(buffer);
END_CRIT_SECTION();
return blkno;
}
/*
* _bt_metapinit() -- Initialize the metadata page of a new btree.
*
* Note: this is actually not used for standard btree index building;
* nbtsort.c prefers not to make the metadata page valid until completion
* of build.
*
* Note: there's no real need for any locking here. Since the transaction
* creating the index hasn't committed yet, no one else can even see the index
* much less be trying to use it. (In a REINDEX-in-place scenario, that's
* not true, but we assume the caller holds sufficient locks on the index.)
*/
void
_bt_metapinit(Relation rel)
{
Buffer buf;
Page pg;
BTMetaPageData *metad;
if (RelationGetNumberOfBlocks(rel) != 0)
elog(ERROR, "cannot initialize non-empty btree index \"%s\"",
RelationGetRelationName(rel));
buf = ReadBuffer(rel, P_NEW);
Assert(BufferGetBlockNumber(buf) == BTREE_METAPAGE);
pg = BufferGetPage(buf);
_bt_initmetapage(pg, P_NONE, 0);
metad = BTPageGetMeta(pg);
/* NO ELOG(ERROR) from here till newmeta op is logged */
START_CRIT_SECTION();
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_newmeta xlrec;
XLogRecPtr recptr;
XLogRecData rdata[1];
xlrec.node = rel->rd_node;
xlrec.meta.root = metad->btm_root;
xlrec.meta.level = metad->btm_level;
xlrec.meta.fastroot = metad->btm_fastroot;
xlrec.meta.fastlevel = metad->btm_fastlevel;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeNewmeta;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = NULL;
recptr = XLogInsert(RM_BTREE_ID,
XLOG_BTREE_NEWMETA,
rdata);
PageSetLSN(pg, recptr);
PageSetTLI(pg, ThisTimeLineID);
}
END_CRIT_SECTION();
WriteBuffer(buf);
}
static void
bitmap_xlog_insert_bitmap_lastwords(bool redo, XLogRecPtr lsn, XLogRecord* record)
{
xl_bm_bitmap_lastwords *xlrec =
(xl_bm_bitmap_lastwords*) XLogRecGetData(record);
Relation reln;
reln = XLogOpenRelation(xlrec->bm_node);
if (!RelationIsValid(reln))
return;
if (redo)
{
Buffer lovBuffer;
Page lovPage;
BMLOVItem lovItem;
#ifdef BM_DEBUG
ereport(LOG, (errcode(LOG),
errmsg("call bitmap_xlog_insert_bitmap_lastwords: redo=%d\n",
redo)));
#endif
lovBuffer = XLogReadBuffer(false, reln, xlrec->bm_lov_blkno);
if (!BufferIsValid(lovBuffer))
elog(PANIC, "bm_insert_redo: block unfound: %d",
xlrec->bm_lov_blkno);
lovPage = BufferGetPage(lovBuffer);
if (XLByteLT(PageGetLSN(lovPage), lsn))
{
lovItem = (BMLOVItem)
PageGetItem(lovPage, PageGetItemId(lovPage, xlrec->bm_lov_offset));
lovItem->bm_last_compword = xlrec->bm_last_compword;
lovItem->bm_last_word = xlrec->bm_last_word;
lovItem->bm_last_two_headerbits = xlrec->bm_last_two_headerbits;
PageSetLSN(lovPage, lsn);
PageSetTLI(lovPage, ThisTimeLineID);
_bitmap_wrtbuf(lovBuffer);
}
else
_bitmap_relbuf(lovBuffer);
}
else
elog(PANIC, "bm_insert_undo: not implemented.");
}
/*
* lazy_vacuum_page() -- free dead tuples on a page
* and repair its fragmentation.
*
* Caller must hold pin and buffer cleanup lock on the buffer.
*
* tupindex is the index in vacrelstats->dead_tuples of the first dead
* tuple for this page. We assume the rest follow sequentially.
* The return value is the first tupindex after the tuples of this page.
*/
static int
lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer,
int tupindex, LVRelStats *vacrelstats)
{
OffsetNumber unused[MaxOffsetNumber];
int uncnt;
Page page = BufferGetPage(buffer);
ItemId itemid;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
START_CRIT_SECTION();
for (; tupindex < vacrelstats->num_dead_tuples; tupindex++)
{
BlockNumber tblk;
OffsetNumber toff;
tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples[tupindex]);
if (tblk != blkno)
break; /* past end of tuples for this block */
toff = ItemPointerGetOffsetNumber(&vacrelstats->dead_tuples[tupindex]);
itemid = PageGetItemId(page, toff);
itemid->lp_flags &= ~LP_USED;
}
uncnt = PageRepairFragmentation(page, unused);
MarkBufferDirty(buffer);
/* XLOG stuff */
if (!onerel->rd_istemp)
{
XLogRecPtr recptr;
recptr = log_heap_clean(onerel, buffer, unused, uncnt);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
else
{
/* No XLOG record, but still need to flag that XID exists on disk */
MyXactMadeTempRelUpdate = true;
}
END_CRIT_SECTION();
return tupindex;
}
/*
* lazy_vacuum_page() -- free dead tuples on a page
* and repair its fragmentation.
*
* Caller must hold pin and buffer cleanup lock on the buffer.
*
* tupindex is the index in vacrelstats->dead_tuples of the first dead
* tuple for this page. We assume the rest follow sequentially.
* The return value is the first tupindex after the tuples of this page.
*/
static int
lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer,
int tupindex, LVRelStats *vacrelstats)
{
Page page = BufferGetPage(buffer);
OffsetNumber unused[MaxOffsetNumber];
int uncnt = 0;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
START_CRIT_SECTION();
for (; tupindex < vacrelstats->num_dead_tuples; tupindex++)
{
BlockNumber tblk;
OffsetNumber toff;
ItemId itemid;
tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples[tupindex]);
if (tblk != blkno)
break; /* past end of tuples for this block */
toff = ItemPointerGetOffsetNumber(&vacrelstats->dead_tuples[tupindex]);
itemid = PageGetItemId(page, toff);
ItemIdSetUnused(itemid);
unused[uncnt++] = toff;
}
PageRepairFragmentation(page);
MarkBufferDirty(buffer);
/* XLOG stuff */
if (!onerel->rd_istemp)
{
XLogRecPtr recptr;
recptr = log_heap_clean(onerel, buffer,
NULL, 0, NULL, 0,
unused, uncnt,
false);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
END_CRIT_SECTION();
return tupindex;
}
/*
* 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;
XLogRecData rdata;
data.node = index->rd_node;
data.ntuples = 0;
data.newRightlink = data.prevTail = InvalidBlockNumber;
memcpy(&data.metadata, metadata, sizeof(GinMetaPageData));
rdata.buffer = InvalidBuffer;
rdata.data = (char *) &data;
rdata.len = sizeof(ginxlogUpdateMeta);
rdata.next = NULL;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE, &rdata);
PageSetLSN(metapage, recptr);
PageSetTLI(metapage, ThisTimeLineID);
}
UnlockReleaseBuffer(metabuffer);
END_CRIT_SECTION();
}
/*
* 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(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);
}
static void
bitmap_xlog_insert_meta(bool redo, XLogRecPtr lsn, XLogRecord* record)
{
xl_bm_metapage *xlrec = (xl_bm_metapage*) XLogRecGetData(record);
Relation reln;
reln = XLogOpenRelation(xlrec->bm_node);
if (!RelationIsValid(reln))
return;
if (redo)
{
Buffer metabuf;
BMMetaPage metapage;
#ifdef BM_DEBUG
ereport(LOG, (errcode(LOG),
errmsg("call bitmap_xlog_insert_meta: redo=%d\n", redo)));
#endif
metabuf = XLogReadBuffer(false, reln, BM_METAPAGE);
if (!BufferIsValid(metabuf))
elog(PANIC, "bm_insert_redo: block unfound: %d", BM_METAPAGE);
/* restore the page */
metapage = (BMMetaPage)BufferGetPage(metabuf);
if (XLByteLT(PageGetLSN(metapage), lsn))
{
PageSetLSN(metapage, lsn);
PageSetTLI(metapage, ThisTimeLineID);
_bitmap_wrtbuf(metabuf);
}
else
_bitmap_relbuf(metabuf);
}
else
elog(PANIC, "bm_insert_undo: not implemented.");
}
/*
* _bitmap_log_lovitem() -- log adding a new lov item to a lov page.
*/
void
_bitmap_log_lovitem(Relation rel, Buffer lovBuffer, bool isNewItem,
OffsetNumber offset, BMLOVItem lovItem)
{
Page lovPage = BufferGetPage(lovBuffer);
/* XLOG stuff */
START_CRIT_SECTION();
if (!(rel->rd_istemp))
{
xl_bm_lovitem xlLovItem;
XLogRecPtr recptr;
XLogRecData rdata[1];
#ifdef BM_DEBUG
elog(LOG, "call _bitmap_log_lovitem: blkno=%d, offset=%d, isNew=%d",
BufferGetBlockNumber(lovBuffer), offset, isNewItem);
#endif
xlLovItem.bm_node = rel->rd_node;
xlLovItem.bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlLovItem.bm_isNewItem = isNewItem;
xlLovItem.bm_lov_offset = offset;
memcpy(&(xlLovItem.bm_lovItem), lovItem,
sizeof(BMLOVItemData));
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlLovItem;
rdata[0].len = sizeof(xl_bm_lovitem);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID,
XLOG_BITMAP_INSERT_LOVITEM, rdata);
PageSetLSN(lovPage, recptr);
PageSetTLI(lovPage, ThisTimeLineID);
}
END_CRIT_SECTION();
}
/*
* _bitmap_log_bitmap_lastwords() -- log the last two words in a bitmap.
*/
void
_bitmap_log_bitmap_lastwords(Relation rel, Buffer lovBuffer,
OffsetNumber lovOffset, BMLOVItem lovItem)
{
/* XLOG stuff */
START_CRIT_SECTION();
if (!(rel->rd_istemp))
{
xl_bm_bitmap_lastwords xlLastwords;
XLogRecPtr recptr;
XLogRecData rdata[1];
#ifdef BM_DEBUG
elog(LOG,
"call _bitmap_log_bitmap_lastwords: lov_blkno=%d, last_compword=%x, last_word=%x",
BufferGetBlockNumber(lovBuffer), lovItem->bm_last_compword,
lovItem->bm_last_word);
#endif
xlLastwords.bm_node = rel->rd_node;
xlLastwords.bm_last_compword = lovItem->bm_last_compword;
xlLastwords.bm_last_word = lovItem->bm_last_word;
xlLastwords.bm_last_two_headerbits = lovItem->bm_last_two_headerbits;
xlLastwords.bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlLastwords.bm_lov_offset = lovOffset;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlLastwords;
rdata[0].len = sizeof(xl_bm_bitmap_lastwords);
rdata[0].next = NULL;
recptr =
XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_INSERT_BITMAP_LASTWORDS, rdata);
PageSetLSN(BufferGetPage(lovBuffer), recptr);
PageSetTLI(BufferGetPage(lovBuffer), ThisTimeLineID);
}
END_CRIT_SECTION();
}
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);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/*
* _bitmap_log_updateword() -- log updating a single word in a given
* bitmap page.
*/
void
_bitmap_log_updateword(Relation rel, Buffer bitmapBuffer, int word_no)
{
Page bitmapPage;
BMBitmap bitmap;
xl_bm_updateword xlBitmapWord;
XLogRecPtr recptr;
XLogRecData rdata[1];
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
bitmapPage = BufferGetPage(bitmapBuffer);
bitmap = (BMBitmap) PageGetContentsMaxAligned(bitmapPage);
xlBitmapWord.bm_node = rel->rd_node;
xlBitmapWord.bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlBitmapWord.bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlBitmapWord.bm_blkno = BufferGetBlockNumber(bitmapBuffer);
xlBitmapWord.bm_word_no = word_no;
xlBitmapWord.bm_cword = bitmap->cwords[word_no];
xlBitmapWord.bm_hword = bitmap->hwords[word_no/BM_HRL_WORD_SIZE];
elog(DEBUG1, "_bitmap_log_updateword: (blkno, word_no, cword, hword)="
"(%d, %d, " INT64_FORMAT ", " INT64_FORMAT ")", xlBitmapWord.bm_blkno,
xlBitmapWord.bm_word_no, xlBitmapWord.bm_cword,
xlBitmapWord.bm_hword);
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlBitmapWord;
rdata[0].len = sizeof(xl_bm_updateword);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_UPDATEWORD, rdata);
PageSetLSN(bitmapPage, recptr);
PageSetTLI(bitmapPage, ThisTimeLineID);
}
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);
}
/*
* 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))));
}