/*
* _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_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);
}
/*
* lazy_vacuum_heap() -- second pass over the heap
*
* This routine marks dead tuples as unused and compacts out free
* space on their pages. Pages not having dead tuples recorded from
* lazy_scan_heap are not visited at all.
*
* Note: the reason for doing this as a second pass is we cannot remove
* the tuples until we've removed their index entries, and we want to
* process index entry removal in batches as large as possible.
*/
static void
lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats)
{
MIRROREDLOCK_BUFMGR_DECLARE;
int tupindex;
int npages;
PGRUsage ru0;
pg_rusage_init(&ru0);
npages = 0;
tupindex = 0;
/* Fetch gp_persistent_relation_node information that will be added to XLOG record. */
RelationFetchGpRelationNodeForXLog(onerel);
while (tupindex < vacrelstats->num_dead_tuples)
{
BlockNumber tblk;
Buffer buf;
Page page;
vacuum_delay_point();
tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples[tupindex]);
/* -------- MirroredLock ---------- */
MIRROREDLOCK_BUFMGR_LOCK;
buf = ReadBufferWithStrategy(onerel, tblk, vac_strategy);
LockBufferForCleanup(buf);
tupindex = lazy_vacuum_page(onerel, tblk, buf, tupindex, vacrelstats);
/* Now that we've compacted the page, record its available space */
page = BufferGetPage(buf);
lazy_record_free_space(vacrelstats, tblk,
PageGetHeapFreeSpace(page));
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
npages++;
}
ereport(elevel,
(errmsg("\"%s\": removed %d row versions in %d pages",
RelationGetRelationName(onerel),
tupindex, npages),
errdetail("%s.",
pg_rusage_show(&ru0))));
}
/*
* _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);
}
/*
* _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);
}
/* ----------------
* index_insert - insert an index tuple into a relation
* ----------------
*/
bool
index_insert(Relation indexRelation,
Datum *values,
bool *isnull,
ItemPointer heap_t_ctid,
Relation heapRelation,
bool check_uniqueness)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
FmgrInfo *procedure;
bool result;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
RELATION_CHECKS;
GET_REL_PROCEDURE(aminsert);
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(indexRelation);
/*
* have the am's insert proc do all the work.
*/
result = DatumGetBool(FunctionCall6(procedure,
PointerGetDatum(indexRelation),
PointerGetDatum(values),
PointerGetDatum(isnull),
PointerGetDatum(heap_t_ctid),
PointerGetDatum(heapRelation),
BoolGetDatum(check_uniqueness)));
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
return result;
}
/*
* Bulk deletion of all index entries pointing to a set of heap tuples.
* The set of target tuples is specified via a callback routine that tells
* whether any given heap tuple (identified by ItemPointer) is being deleted.
*
* Result: a palloc'd struct containing statistical info for VACUUM displays.
*/
Datum
btbulkdelete(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *volatile stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
IndexBulkDeleteCallback callback = (IndexBulkDeleteCallback) PG_GETARG_POINTER(2);
void *callback_state = (void *) PG_GETARG_POINTER(3);
Relation rel = info->index;
BTCycleId cycleid;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
/* allocate stats if first time through, else re-use existing struct */
if (stats == NULL)
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
/* Establish the vacuum cycle ID to use for this scan */
/* The ENSURE stuff ensures we clean up shared memory on failure */
PG_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
{
cycleid = _bt_start_vacuum(rel);
btvacuumscan(info, stats, callback, callback_state, cycleid);
}
PG_END_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
_bt_end_vacuum(rel);
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_POINTER(stats);
}
/*
* _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();
}
/*
* lazy_scan_heap() -- scan an open heap relation
*
* This routine sets commit status bits, builds lists of dead tuples
* and pages with free space, and calculates statistics on the number
* of live tuples in the heap. When done, or when we run low on space
* for dead-tuple TIDs, invoke vacuuming of indexes and heap.
*
* If there are no indexes then we just vacuum each dirty page as we
* process it, since there's no point in gathering many tuples.
*/
static void
lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats,
Relation *Irel, int nindexes, List *updated_stats)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber nblocks,
blkno;
HeapTupleData tuple;
char *relname;
BlockNumber empty_pages,
vacuumed_pages;
double num_tuples,
tups_vacuumed,
nkeep,
nunused;
IndexBulkDeleteResult **indstats;
int i;
int reindex_count = 1;
PGRUsage ru0;
/* Fetch gp_persistent_relation_node information that will be added to XLOG record. */
RelationFetchGpRelationNodeForXLog(onerel);
pg_rusage_init(&ru0);
relname = RelationGetRelationName(onerel);
ereport(elevel,
(errmsg("vacuuming \"%s.%s\"",
get_namespace_name(RelationGetNamespace(onerel)),
relname)));
empty_pages = vacuumed_pages = 0;
num_tuples = tups_vacuumed = nkeep = nunused = 0;
indstats = (IndexBulkDeleteResult **)
palloc0(nindexes * sizeof(IndexBulkDeleteResult *));
nblocks = RelationGetNumberOfBlocks(onerel);
vacrelstats->rel_pages = nblocks;
vacrelstats->nonempty_pages = 0;
lazy_space_alloc(vacrelstats, nblocks);
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
bool tupgone,
hastup;
int prev_dead_count;
OffsetNumber frozen[MaxOffsetNumber];
int nfrozen;
vacuum_delay_point();
/*
* If we are close to overrunning the available space for dead-tuple
* TIDs, pause and do a cycle of vacuuming before we tackle this page.
*/
if ((vacrelstats->max_dead_tuples - vacrelstats->num_dead_tuples) < MaxHeapTuplesPerPage &&
vacrelstats->num_dead_tuples > 0)
{
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i], &indstats[i], vacrelstats);
reindex_count++;
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
/* Forget the now-vacuumed tuples, and press on */
vacrelstats->num_dead_tuples = 0;
vacrelstats->num_index_scans++;
}
/* -------- MirroredLock ---------- */
MIRROREDLOCK_BUFMGR_LOCK;
buf = ReadBufferWithStrategy(onerel, blkno, vac_strategy);
/* We need buffer cleanup lock so that we can prune HOT chains. */
LockBufferForCleanup(buf);
page = BufferGetPage(buf);
if (PageIsNew(page))
{
/*
* An all-zeroes page could be left over if a backend extends the
* relation but crashes before initializing the page. Reclaim such
* pages for use.
*
* We have to be careful here because we could be looking at a
* page that someone has just added to the relation and not yet
* been able to initialize (see RelationGetBufferForTuple). To
* protect against that, release the buffer lock, grab the
* relation extension lock momentarily, and re-lock the buffer. If
* the page is still uninitialized by then, it must be left over
* from a crashed backend, and we can initialize it.
*
* We don't really need the relation lock when this is a new or
* temp relation, but it's probably not worth the code space to
* check that, since this surely isn't a critical path.
*
* Note: the comparable code in vacuum.c need not worry because
* it's got exclusive lock on the whole relation.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
LockRelationForExtension(onerel, ExclusiveLock);
UnlockRelationForExtension(onerel, ExclusiveLock);
/* -------- MirroredLock ---------- */
MIRROREDLOCK_BUFMGR_LOCK;
LockBufferForCleanup(buf);
if (PageIsNew(page))
{
ereport(WARNING,
(errmsg("relation \"%s\" page %u is uninitialized --- fixing",
relname, blkno)));
PageInit(page, BufferGetPageSize(buf), 0);
/* must record in xlog so that changetracking will know about this change */
log_heap_newpage(onerel, page, blkno);
empty_pages++;
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
}
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
continue;
}
if (PageIsEmpty(page))
{
empty_pages++;
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
continue;
}
/*
* Prune all HOT-update chains in this page.
*
* We count tuples removed by the pruning step as removed by VACUUM.
*/
tups_vacuumed += heap_page_prune(onerel, buf, OldestXmin,
false, false);
/*
* Now scan the page to collect vacuumable items and check for tuples
* requiring freezing.
*/
nfrozen = 0;
hastup = false;
prev_dead_count = vacrelstats->num_dead_tuples;
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused items require no processing, but we count 'em */
if (!ItemIdIsUsed(itemid))
{
nunused += 1;
continue;
}
/* Redirect items mustn't be touched */
if (ItemIdIsRedirected(itemid))
{
hastup = true; /* this page won't be truncatable */
continue;
}
ItemPointerSet(&(tuple.t_self), blkno, offnum);
/*
* DEAD item pointers are to be vacuumed normally; but we don't
* count them in tups_vacuumed, else we'd be double-counting (at
* least in the common case where heap_page_prune() just freed up
* a non-HOT tuple).
*/
if (ItemIdIsDead(itemid))
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
continue;
}
Assert(ItemIdIsNormal(itemid));
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tupgone = false;
switch (HeapTupleSatisfiesVacuum(onerel, tuple.t_data, OldestXmin, buf))
{
case HEAPTUPLE_DEAD:
/*
* Ordinarily, DEAD tuples would have been removed by
* heap_page_prune(), but it's possible that the tuple
* state changed since heap_page_prune() looked. In
* particular an INSERT_IN_PROGRESS tuple could have
* changed to DEAD if the inserter aborted. So this
* cannot be considered an error condition.
*
* If the tuple is HOT-updated then it must only be
* removed by a prune operation; so we keep it just as if
* it were RECENTLY_DEAD. Also, if it's a heap-only
* tuple, we choose to keep it, because it'll be a lot
* cheaper to get rid of it in the next pruning pass than
* to treat it like an indexed tuple.
*/
if (HeapTupleIsHotUpdated(&tuple) ||
HeapTupleIsHeapOnly(&tuple))
nkeep += 1;
else
tupgone = true; /* we can delete the tuple */
break;
case HEAPTUPLE_LIVE:
/* Tuple is good --- but let's do some validity checks */
if (onerel->rd_rel->relhasoids &&
!OidIsValid(HeapTupleGetOid(&tuple)))
elog(WARNING, "relation \"%s\" TID %u/%u: OID is invalid",
relname, blkno, offnum);
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must not remove it
* from relation.
*/
nkeep += 1;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (tupgone)
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
tups_vacuumed += 1;
}
else
{
num_tuples += 1;
hastup = true;
/*
* Each non-removable tuple must be checked to see if it needs
* freezing. Note we already have exclusive buffer lock.
*/
if (heap_freeze_tuple(tuple.t_data, &FreezeLimit,
InvalidBuffer, false))
frozen[nfrozen++] = offnum;
}
} /* scan along page */
/*
* If we froze any tuples, mark the buffer dirty, and write a WAL
* record recording the changes. We must log the changes to be
* crash-safe against future truncation of CLOG.
*/
if (nfrozen > 0)
{
MarkBufferDirty(buf);
/* no XLOG for temp tables, though */
if (!onerel->rd_istemp)
{
XLogRecPtr recptr;
recptr = log_heap_freeze(onerel, buf, FreezeLimit,
frozen, nfrozen);
PageSetLSN(page, recptr);
}
}
/*
* If there are no indexes then we can vacuum the page right now
* instead of doing a second scan.
*/
if (nindexes == 0 &&
vacrelstats->num_dead_tuples > 0)
{
/* Remove tuples from heap */
lazy_vacuum_page(onerel, blkno, buf, 0, vacrelstats);
/* Forget the now-vacuumed tuples, and press on */
vacrelstats->num_dead_tuples = 0;
vacuumed_pages++;
}
/*
* If we remembered any tuples for deletion, then the page will be
* visited again by lazy_vacuum_heap, which will compute and record
* its post-compaction free space. If not, then we're done with this
* page, so remember its free space as-is. (This path will always be
* taken if there are no indexes.)
*/
if (vacrelstats->num_dead_tuples == prev_dead_count)
{
lazy_record_free_space(vacrelstats, blkno,
PageGetHeapFreeSpace(page));
}
/* Remember the location of the last page with nonremovable tuples */
if (hastup)
vacrelstats->nonempty_pages = blkno + 1;
UnlockReleaseBuffer(buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
/* -------- MirroredLock ---------- */
}
/* save stats for use later */
vacrelstats->rel_tuples = num_tuples;
vacrelstats->tuples_deleted = tups_vacuumed;
/* If any tuples need to be deleted, perform final vacuum cycle */
/* XXX put a threshold on min number of tuples here? */
if (vacrelstats->num_dead_tuples > 0)
{
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i], &indstats[i], vacrelstats);
reindex_count++;
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
vacrelstats->num_index_scans++;
}
/* Do post-vacuum cleanup and statistics update for each index */
for (i = 0; i < nindexes; i++)
lazy_cleanup_index(Irel[i], indstats[i], vacrelstats, updated_stats);
/* If no indexes, make log report that lazy_vacuum_heap would've made */
if (vacuumed_pages)
ereport(elevel,
(errmsg("\"%s\": removed %.0f row versions in %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, vacuumed_pages)));
ereport(elevel,
(errmsg("\"%s\": found %.0f removable, %.0f nonremovable row versions in %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, num_tuples, nblocks),
errdetail("%.0f dead row versions cannot be removed yet.\n"
"There were %.0f unused item pointers.\n"
"%u pages contain useful free space.\n"
"%u pages are entirely empty.\n"
"%s.",
nkeep,
nunused,
vacrelstats->tot_free_pages,
empty_pages,
pg_rusage_show(&ru0))));
}
/*
* _bitmap_log_bitmapwords() -- log new bitmap words to be inserted.
*/
void
_bitmap_log_bitmapwords(Relation rel, Buffer bitmapBuffer, Buffer lovBuffer,
OffsetNumber lovOffset, BMTIDBuffer* buf,
uint64 words_written, uint64 tidnum, BlockNumber nextBlkno,
bool isLast, bool isFirst)
{
Page bitmapPage;
BMBitmapOpaque bitmapPageOpaque;
xl_bm_bitmapwords *xlBitmapWords;
XLogRecPtr recptr;
XLogRecData rdata[1];
uint64* lastTids;
BM_HRL_WORD* cwords;
BM_HRL_WORD* hwords;
int lastTids_size;
int cwords_size;
int hwords_size;
Page lovPage = BufferGetPage(lovBuffer);
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
lastTids_size = buf->curword * sizeof(uint64);
cwords_size = buf->curword * sizeof(BM_HRL_WORD);
hwords_size = (BM_CALC_H_WORDS(buf->curword)) *
sizeof(BM_HRL_WORD);
bitmapPage = BufferGetPage(bitmapBuffer);
bitmapPageOpaque =
(BMBitmapOpaque)PageGetSpecialPointer(bitmapPage);
xlBitmapWords = (xl_bm_bitmapwords *)
palloc0(MAXALIGN(sizeof(xl_bm_bitmapwords)) + MAXALIGN(lastTids_size) +
MAXALIGN(cwords_size) + MAXALIGN(hwords_size));
xlBitmapWords->bm_node = rel->rd_node;
xlBitmapWords->bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlBitmapWords->bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlBitmapWords->bm_blkno = BufferGetBlockNumber(bitmapBuffer);
xlBitmapWords->bm_next_blkno = nextBlkno;
xlBitmapWords->bm_last_tid = bitmapPageOpaque->bm_last_tid_location;
xlBitmapWords->bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlBitmapWords->bm_lov_offset = lovOffset;
xlBitmapWords->bm_last_compword = buf->last_compword;
xlBitmapWords->bm_last_word = buf->last_word;
xlBitmapWords->lov_words_header =
(buf->is_last_compword_fill) ? 2 : 0;
xlBitmapWords->bm_last_setbit = tidnum;
xlBitmapWords->bm_is_last = isLast;
xlBitmapWords->bm_is_first = isFirst;
xlBitmapWords->bm_start_wordno = buf->start_wordno;
xlBitmapWords->bm_words_written = words_written;
xlBitmapWords->bm_num_cwords = buf->curword;
lastTids = (uint64*)(((char*)xlBitmapWords) +
MAXALIGN(sizeof(xl_bm_bitmapwords)));
memcpy(lastTids, buf->last_tids,
buf->curword * sizeof(uint64));
cwords = (BM_HRL_WORD*)(((char*)xlBitmapWords) +
MAXALIGN(sizeof(xl_bm_bitmapwords)) + MAXALIGN(lastTids_size));
memcpy(cwords, buf->cwords, cwords_size);
hwords = (BM_HRL_WORD*)(((char*)xlBitmapWords) +
MAXALIGN(sizeof(xl_bm_bitmapwords)) + MAXALIGN(lastTids_size) +
MAXALIGN(cwords_size));
memcpy(hwords, buf->hwords, hwords_size);
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)xlBitmapWords;
rdata[0].len = MAXALIGN(sizeof(xl_bm_bitmapwords)) + MAXALIGN(lastTids_size) +
MAXALIGN(cwords_size) + MAXALIGN(hwords_size);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_INSERT_WORDS, rdata);
PageSetLSN(bitmapPage, recptr);
PageSetTLI(bitmapPage, ThisTimeLineID);
PageSetLSN(lovPage, recptr);
PageSetTLI(lovPage, ThisTimeLineID);
pfree(xlBitmapWords);
}
/*
* _bitmap_log_updatewords() -- log updating bitmap words in one or
* two bitmap pages.
*
* If nextBuffer is Invalid, we only update one page.
*
*/
void
_bitmap_log_updatewords(Relation rel,
Buffer lovBuffer, OffsetNumber lovOffset,
Buffer firstBuffer, Buffer secondBuffer,
bool new_lastpage)
{
Page firstPage = NULL;
Page secondPage = NULL;
BMBitmap firstBitmap;
BMBitmap secondBitmap;
BMBitmapOpaque firstOpaque;
BMBitmapOpaque secondOpaque;
xl_bm_updatewords xlBitmapWords;
XLogRecPtr recptr;
XLogRecData rdata[1];
firstPage = BufferGetPage(firstBuffer);
firstBitmap = (BMBitmap) PageGetContentsMaxAligned(firstPage);
firstOpaque = (BMBitmapOpaque)PageGetSpecialPointer(firstPage);
xlBitmapWords.bm_two_pages = false;
xlBitmapWords.bm_first_blkno = BufferGetBlockNumber(firstBuffer);
memcpy(&xlBitmapWords.bm_first_cwords,
firstBitmap->cwords,
BM_NUM_OF_HRL_WORDS_PER_PAGE * sizeof(BM_HRL_WORD));
memcpy(&xlBitmapWords.bm_first_hwords,
firstBitmap->hwords,
BM_NUM_OF_HEADER_WORDS * sizeof(BM_HRL_WORD));
xlBitmapWords.bm_first_last_tid = firstOpaque->bm_last_tid_location;
xlBitmapWords.bm_first_num_cwords =
firstOpaque->bm_hrl_words_used;
xlBitmapWords.bm_next_blkno = firstOpaque->bm_bitmap_next;
if (BufferIsValid(secondBuffer))
{
secondPage = BufferGetPage(secondBuffer);
secondBitmap = (BMBitmap) PageGetContentsMaxAligned(secondPage);
secondOpaque = (BMBitmapOpaque)PageGetSpecialPointer(secondPage);
xlBitmapWords.bm_two_pages = true;
xlBitmapWords.bm_second_blkno = BufferGetBlockNumber(secondBuffer);
memcpy(&xlBitmapWords.bm_second_cwords,
secondBitmap->cwords,
BM_NUM_OF_HRL_WORDS_PER_PAGE * sizeof(BM_HRL_WORD));
memcpy(&xlBitmapWords.bm_second_hwords,
secondBitmap->hwords,
BM_NUM_OF_HEADER_WORDS * sizeof(BM_HRL_WORD));
xlBitmapWords.bm_second_last_tid = secondOpaque->bm_last_tid_location;
xlBitmapWords.bm_second_num_cwords =
secondOpaque->bm_hrl_words_used;
xlBitmapWords.bm_next_blkno = secondOpaque->bm_bitmap_next;
}
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
xlBitmapWords.bm_node = rel->rd_node;
xlBitmapWords.bm_persistentTid = rel->rd_relationnodeinfo.persistentTid;
xlBitmapWords.bm_persistentSerialNum = rel->rd_relationnodeinfo.persistentSerialNum;
xlBitmapWords.bm_lov_blkno = BufferGetBlockNumber(lovBuffer);
xlBitmapWords.bm_lov_offset = lovOffset;
xlBitmapWords.bm_new_lastpage = new_lastpage;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char*)&xlBitmapWords;
rdata[0].len = sizeof(xl_bm_updatewords);
rdata[0].next = NULL;
recptr = XLogInsert(RM_BITMAP_ID, XLOG_BITMAP_UPDATEWORDS, rdata);
PageSetLSN(firstPage, recptr);
PageSetTLI(firstPage, ThisTimeLineID);
if (BufferIsValid(secondBuffer))
{
PageSetLSN(secondPage, recptr);
PageSetTLI(secondPage, ThisTimeLineID);
}
if (new_lastpage)
{
Page lovPage = BufferGetPage(lovBuffer);
PageSetLSN(lovPage, recptr);
PageSetTLI(lovPage, ThisTimeLineID);
}
}
void
_bitmap_create_lov_heapandindex(Relation rel,
Oid lovComptypeOid,
Oid *lovHeapOid,
Oid *lovIndexOid,
Oid lovHeapRelfilenode,
Oid lovIndexRelfilenode)
{
char lovHeapName[NAMEDATALEN];
char lovIndexName[NAMEDATALEN];
TupleDesc tupDesc;
IndexInfo *indexInfo;
ObjectAddress objAddr, referenced;
Oid *classObjectId;
int16 *coloptions;
Oid heapid;
Oid idxid;
int indattrs;
int i;
Oid unusedArrayOid = InvalidOid;
Assert(rel != NULL);
/* create the new names for the new lov heap and index */
snprintf(lovHeapName, sizeof(lovHeapName),
"pg_bm_%u", RelationGetRelid(rel));
snprintf(lovIndexName, sizeof(lovIndexName),
"pg_bm_%u_index", RelationGetRelid(rel));
heapid = get_relname_relid(lovHeapName, PG_BITMAPINDEX_NAMESPACE);
/*
* If heapid exists, then this is happening during re-indexing.
* We allocate new relfilenodes for lov heap and lov index.
*
* XXX Each segment db may have different relfilenodes for lov heap and
* lov index, which should not be an issue now. Ideally, we would like each
* segment db use the same oids.
*/
if (OidIsValid(heapid))
{
Relation lovHeap;
Relation lovIndex;
Buffer btree_metabuf;
Page btree_metapage;
*lovHeapOid = heapid;
idxid = get_relname_relid(lovIndexName, PG_BITMAPINDEX_NAMESPACE);
Assert(OidIsValid(idxid));
*lovIndexOid = idxid;
lovComptypeOid = get_rel_type_id(heapid);
Assert(OidIsValid(lovComptypeOid));
lovHeap = heap_open(heapid, AccessExclusiveLock);
lovIndex = index_open(idxid, AccessExclusiveLock);
if (OidIsValid(lovHeapRelfilenode))
setNewRelfilenodeToOid(lovHeap, lovHeapRelfilenode);
else
setNewRelfilenode(lovHeap);
if (OidIsValid(lovIndexRelfilenode))
setNewRelfilenodeToOid(lovIndex, lovIndexRelfilenode);
else
setNewRelfilenode(lovIndex);
/*
* After creating the new relfilenode for a btee index, this is not
* a btree anymore. We create the new metapage for this btree.
*/
btree_metabuf = _bt_getbuf(lovIndex, P_NEW, BT_WRITE);
Assert (BTREE_METAPAGE == BufferGetBlockNumber(btree_metabuf));
btree_metapage = BufferGetPage(btree_metabuf);
_bt_initmetapage(btree_metapage, P_NONE, 0);
/* XLOG the metapage */
if (!XLog_UnconvertedCanBypassWal() && !lovIndex->rd_istemp)
{
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(lovIndex);
_bt_lognewpage(lovIndex,
btree_metapage,
BufferGetBlockNumber(btree_metabuf));
}
/* This cache value is not valid anymore. */
if (lovIndex->rd_amcache)
{
pfree(lovIndex->rd_amcache);
lovIndex->rd_amcache = NULL;
}
MarkBufferDirty(btree_metabuf);
_bt_relbuf(lovIndex, btree_metabuf);
index_close(lovIndex, NoLock);
heap_close(lovHeap, NoLock);
return;
}
/*
* create a new empty heap to store all attribute values with their
* corresponding block number and offset in LOV.
*/
tupDesc = _bitmap_create_lov_heapTupleDesc(rel);
Assert(rel->rd_rel != NULL);
heapid =
heap_create_with_catalog(lovHeapName, PG_BITMAPINDEX_NAMESPACE,
rel->rd_rel->reltablespace,
*lovHeapOid, rel->rd_rel->relowner,
tupDesc,
/* relam */ InvalidOid, RELKIND_RELATION, RELSTORAGE_HEAP,
rel->rd_rel->relisshared, false, /* bufferPoolBulkLoad */ false, 0,
ONCOMMIT_NOOP, NULL /* GP Policy */,
(Datum)0, true,
/* valid_opts */ true,
&lovComptypeOid,
&unusedArrayOid,
/* persistentTid */ NULL,
/* persistentSerialNum */ NULL);
Assert(heapid == *lovHeapOid);
/*
* We must bump the command counter to make the newly-created relation
* tuple visible for opening.
*/
CommandCounterIncrement();
objAddr.classId = RelationRelationId;
objAddr.objectId = *lovHeapOid;
objAddr.objectSubId = 0 ;
referenced.classId = RelationRelationId;
referenced.objectId = RelationGetRelid(rel);
referenced.objectSubId = 0;
recordDependencyOn(&objAddr, &referenced, DEPENDENCY_INTERNAL);
/*
* create a btree index on the newly-created heap.
* The key includes all attributes to be indexed in this bitmap index.
*/
indattrs = tupDesc->natts - 2;
indexInfo = makeNode(IndexInfo);
indexInfo->ii_NumIndexAttrs = indattrs;
indexInfo->ii_Expressions = NIL;
indexInfo->ii_ExpressionsState = NIL;
indexInfo->ii_Predicate = make_ands_implicit(NULL);
indexInfo->ii_PredicateState = NIL;
indexInfo->ii_Unique = true;
indexInfo->opaque = NULL;
classObjectId = (Oid *) palloc(indattrs * sizeof(Oid));
coloptions = (int16 *) palloc(indattrs * sizeof(int16));
for (i = 0; i < indattrs; i++)
{
Oid typid = tupDesc->attrs[i]->atttypid;
indexInfo->ii_KeyAttrNumbers[i] = i + 1;
classObjectId[i] = GetDefaultOpClass(typid, BTREE_AM_OID);
coloptions[i] = 0;
}
idxid = index_create(*lovHeapOid, lovIndexName, *lovIndexOid,
indexInfo, BTREE_AM_OID,
rel->rd_rel->reltablespace,
classObjectId, coloptions, 0, false, false, (Oid *) NULL, true,
false, false, NULL);
Assert(idxid == *lovIndexOid);
}
/*
* emit a completed btree page, and release the working storage.
*/
static void
_bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
{
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(wstate->index);
/* Ensure rd_smgr is open (could have been closed by relcache flush!) */
RelationOpenSmgr(wstate->index);
/* XLOG stuff */
if (wstate->btws_use_wal)
{
_bt_lognewpage(wstate->index, page, blkno);
}
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);
// -------- MirroredLock ----------
// UNDONE: Unfortunately, I think we write temp relations to the mirror...
LWLockAcquire(MirroredLock, LW_SHARED);
smgrextend(wstate->index->rd_smgr, wstate->btws_pages_written++,
(char *) wstate->btws_zeropage,
true);
LWLockRelease(MirroredLock);
// -------- MirroredLock ----------
}
// -------- MirroredLock ----------
// UNDONE: Unfortunately, I think we write temp relations to the mirror...
LWLockAcquire(MirroredLock, LW_SHARED);
/*
* 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, blkno, (char *) page, true);
wstate->btws_pages_written++;
}
else
{
/* overwriting a block we zero-filled before */
smgrwrite(wstate->index->rd_smgr, blkno, (char *) page, true);
}
LWLockRelease(MirroredLock);
// -------- MirroredLock ----------
pfree(page);
}
