/*
* Guts of rule deletion.
*/
void
RemoveRewriteRuleById(Oid ruleOid)
{
Relation RewriteRelation;
ScanKeyData skey[1];
SysScanDesc rcscan;
Relation event_relation;
HeapTuple tuple;
Oid eventRelationOid;
/*
* Open the pg_rewrite relation.
*/
RewriteRelation = heap_open(RewriteRelationId, RowExclusiveLock);
/*
* Find the tuple for the target rule.
*/
ScanKeyInit(&skey[0],
ObjectIdAttributeNumber,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(ruleOid));
rcscan = systable_beginscan(RewriteRelation, RewriteOidIndexId, true,
NULL, 1, skey);
tuple = systable_getnext(rcscan);
if (!HeapTupleIsValid(tuple))
elog(ERROR, "could not find tuple for rule %u", ruleOid);
/*
* We had better grab AccessExclusiveLock to ensure that no queries are
* going on that might depend on this rule. (Note: a weaker lock would
* suffice if it's not an ON SELECT rule.)
*/
eventRelationOid = ((Form_pg_rewrite) GETSTRUCT(tuple))->ev_class;
event_relation = heap_open(eventRelationOid, AccessExclusiveLock);
/*
* Now delete the pg_rewrite tuple for the rule
*/
simple_heap_delete(RewriteRelation, &tuple->t_self);
systable_endscan(rcscan);
heap_close(RewriteRelation, RowExclusiveLock);
/*
* Issue shared-inval notice to force all backends (including me!) to
* update relcache entries with the new___ rule set.
*/
CacheInvalidateRelcache(event_relation);
/* Close rel, but keep lock till commit... */
heap_close(event_relation, NoLock);
}
/*
* Ensure that the visibility map fork is at least vm_nblocks long, extending
* it if necessary with zeroed pages.
*/
static void
vm_extend(Relation rel, BlockNumber vm_nblocks)
{
BlockNumber vm_nblocks_now;
Page pg;
pg = (Page) palloc(BLCKSZ);
PageInit(pg, BLCKSZ, 0);
/*
* We use the relation extension lock to lock out other backends trying to
* extend the visibility map at the same time. It also locks out extension
* of the main fork, unnecessarily, but extending the visibility map
* happens seldom enough that it doesn't seem worthwhile to have a
* separate lock tag type for it.
*
* Note that another backend might have extended or created the relation
* before we get the lock.
*/
LockRelationForExtension(rel, ExclusiveLock);
/* Create the file first if it doesn't exist */
if ((rel->rd_vm_nblocks == 0 || rel->rd_vm_nblocks == InvalidBlockNumber)
&& !smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
{
smgrcreate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, false);
vm_nblocks_now = 0;
}
else
vm_nblocks_now = smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM);
while (vm_nblocks_now < vm_nblocks)
{
smgrextend(rel->rd_smgr, VISIBILITYMAP_FORKNUM, vm_nblocks_now,
(char *) pg, rel->rd_istemp);
vm_nblocks_now++;
}
UnlockRelationForExtension(rel, ExclusiveLock);
pfree(pg);
/* Update the relcache with the up-to-date size */
if (!InRecovery)
CacheInvalidateRelcache(rel);
rel->rd_vm_nblocks = vm_nblocks_now;
}
/*
* _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;
}
/*
* Insert new publication / relation mapping.
*/
ObjectAddress
publication_add_relation(Oid pubid, Relation targetrel,
bool if_not_exists)
{
Relation rel;
HeapTuple tup;
Datum values[Natts_pg_publication_rel];
bool nulls[Natts_pg_publication_rel];
Oid relid = RelationGetRelid(targetrel);
Oid prrelid;
Publication *pub = GetPublication(pubid);
ObjectAddress myself,
referenced;
rel = heap_open(PublicationRelRelationId, RowExclusiveLock);
/*
* Check for duplicates. Note that this does not really prevent
* duplicates, it's here just to provide nicer error message in common
* case. The real protection is the unique key on the catalog.
*/
if (SearchSysCacheExists2(PUBLICATIONRELMAP, ObjectIdGetDatum(relid),
ObjectIdGetDatum(pubid)))
{
heap_close(rel, RowExclusiveLock);
if (if_not_exists)
return InvalidObjectAddress;
ereport(ERROR,
(errcode(ERRCODE_DUPLICATE_OBJECT),
errmsg("relation \"%s\" is already member of publication \"%s\"",
RelationGetRelationName(targetrel), pub->name)));
}
check_publication_add_relation(targetrel);
/* Form a tuple. */
memset(values, 0, sizeof(values));
memset(nulls, false, sizeof(nulls));
prrelid = GetNewOidWithIndex(rel, PublicationRelObjectIndexId,
Anum_pg_publication_rel_oid);
values[Anum_pg_publication_rel_oid - 1] = ObjectIdGetDatum(prrelid);
values[Anum_pg_publication_rel_prpubid - 1] =
ObjectIdGetDatum(pubid);
values[Anum_pg_publication_rel_prrelid - 1] =
ObjectIdGetDatum(relid);
tup = heap_form_tuple(RelationGetDescr(rel), values, nulls);
/* Insert tuple into catalog. */
CatalogTupleInsert(rel, tup);
heap_freetuple(tup);
ObjectAddressSet(myself, PublicationRelRelationId, prrelid);
/* Add dependency on the publication */
ObjectAddressSet(referenced, PublicationRelationId, pubid);
recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
/* Add dependency on the relation */
ObjectAddressSet(referenced, RelationRelationId, relid);
recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
/* Close the table. */
heap_close(rel, RowExclusiveLock);
/* Invalidate relcache so that publication info is rebuilt. */
CacheInvalidateRelcache(targetrel);
return myself;
}
/*
* visibilitymap_test - truncate the visibility map
*/
void
visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
{
BlockNumber newnblocks;
/* last remaining block, byte, and bit */
BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks);
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
/*
* If no visibility map has been created yet for this relation, there's
* nothing to truncate.
*/
if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
return;
/*
* Unless the new size is exactly at a visibility map page boundary, the
* tail bits in the last remaining map page, representing truncated heap
* blocks, need to be cleared. This is not only tidy, but also necessary
* because we don't get a chance to clear the bits if the heap is extended
* again.
*/
if (truncByte != 0 || truncBit != 0)
{
Buffer mapBuffer;
Page page;
char *map;
newnblocks = truncBlock + 1;
mapBuffer = vm_readbuf(rel, truncBlock, false);
if (!BufferIsValid(mapBuffer))
{
/* nothing to do, the file was already smaller */
return;
}
page = BufferGetPage(mapBuffer);
map = PageGetContents(page);
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
/* Clear out the unwanted bytes. */
MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
/*
* Mask out the unwanted bits of the last remaining byte.
*
* ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) -
* 1) = 00111111 ((1 << 7) - 1) = 01111111
*/
map[truncByte] &= (1 << truncBit) - 1;
MarkBufferDirty(mapBuffer);
UnlockReleaseBuffer(mapBuffer);
}
else
newnblocks = truncBlock;
if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) < newnblocks)
{
/* nothing to do, the file was already smaller than requested size */
return;
}
smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks,
rel->rd_istemp);
/*
* Need to invalidate the relcache entry, because rd_vm_nblocks seen by
* other backends is no longer valid.
*/
if (!InRecovery)
CacheInvalidateRelcache(rel);
rel->rd_vm_nblocks = newnblocks;
}
/* ----------------
* set relhasindex of relation's pg_class entry
*
* If isprimary is TRUE, we are defining a primary index, so also set
* relhaspkey to TRUE. Otherwise, leave relhaspkey alone.
*
* If reltoastidxid is not InvalidOid, also set reltoastidxid to that value.
* This is only used for TOAST relations.
*
* NOTE: an important side-effect of this operation is that an SI invalidation
* message is sent out to all backends --- including me --- causing relcache
* entries to be flushed or updated with the new hasindex data. This must
* happen even if we find that no change is needed in the pg_class row.
* ----------------
*/
void
setRelhasindex(Oid relid, bool hasindex, bool isprimary, Oid reltoastidxid)
{
Relation pg_class;
HeapTuple tuple;
Form_pg_class classtuple;
bool dirty = false;
HeapScanDesc pg_class_scan = NULL;
/*
* Find the tuple to update in pg_class. In bootstrap mode we can't
* use heap_update, so cheat and overwrite the tuple in-place. In
* normal processing, make a copy to scribble on.
*/
pg_class = heap_openr(RelationRelationName, RowExclusiveLock);
if (!IsBootstrapProcessingMode())
{
tuple = SearchSysCacheCopy(RELOID,
ObjectIdGetDatum(relid),
0, 0, 0);
}
else
{
ScanKeyData key[1];
ScanKeyEntryInitialize(&key[0], 0,
ObjectIdAttributeNumber,
F_OIDEQ,
ObjectIdGetDatum(relid));
pg_class_scan = heap_beginscan(pg_class, SnapshotNow, 1, key);
tuple = heap_getnext(pg_class_scan, ForwardScanDirection);
}
if (!HeapTupleIsValid(tuple))
elog(ERROR, "could not find tuple for relation %u", relid);
classtuple = (Form_pg_class) GETSTRUCT(tuple);
/* Apply required updates */
if (pg_class_scan)
LockBuffer(pg_class_scan->rs_cbuf, BUFFER_LOCK_EXCLUSIVE);
if (classtuple->relhasindex != hasindex)
{
classtuple->relhasindex = hasindex;
dirty = true;
}
if (isprimary)
{
if (!classtuple->relhaspkey)
{
classtuple->relhaspkey = true;
dirty = true;
}
}
if (OidIsValid(reltoastidxid))
{
Assert(classtuple->relkind == RELKIND_TOASTVALUE);
if (classtuple->reltoastidxid != reltoastidxid)
{
classtuple->reltoastidxid = reltoastidxid;
dirty = true;
}
}
if (pg_class_scan)
LockBuffer(pg_class_scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
if (pg_class_scan)
{
/* Write the modified tuple in-place */
WriteNoReleaseBuffer(pg_class_scan->rs_cbuf);
/* Send out shared cache inval if necessary */
if (!IsBootstrapProcessingMode())
CacheInvalidateHeapTuple(pg_class, tuple);
BufferSync();
}
else if (dirty)
{
simple_heap_update(pg_class, &tuple->t_self, tuple);
/* Keep the catalog indexes up to date */
CatalogUpdateIndexes(pg_class, tuple);
}
else
{
/* no need to change tuple, but force relcache rebuild anyway */
CacheInvalidateRelcache(relid);
}
if (!pg_class_scan)
heap_freetuple(tuple);
else
heap_endscan(pg_class_scan);
heap_close(pg_class, RowExclusiveLock);
}
/*
* index_drop
*
* NOTE: this routine should now only be called through performDeletion(),
* else associated dependencies won't be cleaned up.
*/
void
index_drop(Oid indexId)
{
Oid heapId;
Relation userHeapRelation;
Relation userIndexRelation;
Relation indexRelation;
HeapTuple tuple;
int i;
Assert(OidIsValid(indexId));
/*
* To drop an index safely, we must grab exclusive lock on its parent
* table; otherwise there could be other backends using the index!
* Exclusive lock on the index alone is insufficient because another
* backend might be in the midst of devising a query plan that will
* use the index. The parser and planner take care to hold an
* appropriate lock on the parent table while working, but having them
* hold locks on all the indexes too seems overly complex. We do grab
* exclusive lock on the index too, just to be safe. Both locks must
* be held till end of transaction, else other backends will still see
* this index in pg_index.
*/
heapId = IndexGetRelation(indexId);
userHeapRelation = heap_open(heapId, AccessExclusiveLock);
userIndexRelation = index_open(indexId);
LockRelation(userIndexRelation, AccessExclusiveLock);
/*
* fix RELATION relation
*/
DeleteRelationTuple(indexId);
/*
* fix ATTRIBUTE relation
*/
DeleteAttributeTuples(indexId);
/*
* fix INDEX relation
*/
indexRelation = heap_openr(IndexRelationName, RowExclusiveLock);
tuple = SearchSysCache(INDEXRELID,
ObjectIdGetDatum(indexId),
0, 0, 0);
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for index %u", indexId);
simple_heap_delete(indexRelation, &tuple->t_self);
ReleaseSysCache(tuple);
heap_close(indexRelation, RowExclusiveLock);
/*
* flush buffer cache and physically remove the file
*/
i = FlushRelationBuffers(userIndexRelation, (BlockNumber) 0);
if (i < 0)
elog(ERROR, "FlushRelationBuffers returned %d", i);
smgrunlink(DEFAULT_SMGR, userIndexRelation);
/*
* We are presently too lazy to attempt to compute the new correct
* value of relhasindex (the next VACUUM will fix it if necessary). So
* there is no need to update the pg_class tuple for the owning
* relation. But we must send out a shared-cache-inval notice on the
* owning relation to ensure other backends update their relcache
* lists of indexes.
*/
CacheInvalidateRelcache(heapId);
/*
* Close rels, but keep locks
*/
index_close(userIndexRelation);
heap_close(userHeapRelation, NoLock);
RelationForgetRelation(indexId);
}
