/*
* _bt_moveright() -- move right in the btree if necessary.
*
* When we follow a pointer to reach a page, it is possible that
* the page has changed in the meanwhile. If this happens, we're
* guaranteed that the page has "split right" -- that is, that any
* data that appeared on the page originally is either on the page
* or strictly to the right of it.
*
* This routine decides whether or not we need to move right in the
* tree by examining the high key entry on the page. If that entry
* is strictly less than one we expect to be on the page, then our
* picture of the page is incorrect and we need to move right.
*
* On entry, we have the buffer pinned and a lock of the proper type.
* If we move right, we release the buffer and lock and acquire the
* same on the right sibling. Return value is the buffer we stop at.
*/
Buffer
_bt_moveright(Relation rel,
Buffer buf,
int keysz,
ScanKey scankey,
int access)
{
Page page;
BTPageOpaque opaque;
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* If the scan key that brought us to this page is > the high key
* stored on the page, then the page has split and we need to move
* right. (If the scan key is equal to the high key, we might or
* might not need to move right; have to scan the page first anyway.)
* It could even have split more than once, so scan as far as needed.
*
* We also have to move right if we followed a link that brought us to a
* dead page.
*/
while (!P_RIGHTMOST(opaque) &&
(P_IGNORE(opaque) ||
_bt_compare(rel, keysz, scankey, page, P_HIKEY) > 0))
{
/* step right one page */
BlockNumber rblkno = opaque->btpo_next;
_bt_relbuf(rel, buf);
buf = _bt_getbuf(rel, rblkno, access);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
if (P_IGNORE(opaque))
elog(ERROR, "fell off the end of \"%s\"",
RelationGetRelationName(rel));
return buf;
}
/*
* _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;
}
/*
* _bt_gettrueroot() -- Get the true root page of the btree.
*
* This is the same as the BT_READ case of _bt_getroot(), except
* we follow the true-root link not the fast-root link.
*
* By the time we acquire lock on the root page, it might have been split and
* not be the true root anymore. This is okay for the present uses of this
* routine; we only really need to be able to move up at least one tree level
* from whatever non-root page we were at. If we ever do need to lock the
* one true root page, we could loop here, re-reading the metapage on each
* failure. (Note that it wouldn't do to hold the lock on the metapage while
* moving to the root --- that'd deadlock against any concurrent root split.)
*/
Buffer
_bt_gettrueroot(Relation rel)
{
Buffer metabuf;
Page metapg;
BTPageOpaque metaopaque;
Buffer rootbuf;
Page rootpage;
BTPageOpaque rootopaque;
BlockNumber rootblkno;
uint32 rootlevel;
BTMetaPageData *metad;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
/*
* We don't try to use cached metapage data here, since (a) this path is
* not performance-critical, and (b) if we are here it suggests our cache
* is out-of-date anyway. In light of point (b), it's probably safest to
* actively flush any cached metapage info.
*/
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);
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, fail */
if (metad->btm_root == P_NONE)
{
_bt_relbuf(rel, metabuf);
return InvalidBuffer;
}
rootblkno = metad->btm_root;
rootlevel = metad->btm_level;
/*
* 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);
return rootbuf;
}
/*
* _bt_moveright() -- move right in the btree if necessary.
*
* When we follow a pointer to reach a page, it is possible that
* the page has changed in the meanwhile. If this happens, we're
* guaranteed that the page has "split right" -- that is, that any
* data that appeared on the page originally is either on the page
* or strictly to the right of it.
*
* This routine decides whether or not we need to move right in the
* tree by examining the high key entry on the page. If that entry
* is strictly less than the scankey, or <= the scankey in the nextkey=true
* case, then we followed the wrong link and we need to move right.
*
* The passed scankey must be an insertion-type scankey (see nbtree/README),
* but it can omit the rightmost column(s) of the index.
*
* When nextkey is false (the usual case), we are looking for the first
* item >= scankey. When nextkey is true, we are looking for the first
* item strictly greater than scankey.
*
* If forupdate is true, we will attempt to finish any incomplete splits
* that we encounter. This is required when locking a target page for an
* insertion, because we don't allow inserting on a page before the split
* is completed. 'stack' is only used if forupdate is true.
*
* On entry, we have the buffer pinned and a lock of the type specified by
* 'access'. If we move right, we release the buffer and lock and acquire
* the same on the right sibling. Return value is the buffer we stop at.
*/
Buffer
_bt_moveright(Relation rel,
Buffer buf,
int keysz,
ScanKey scankey,
bool nextkey,
bool forupdate,
BTStack stack,
int access)
{
Page page;
BTPageOpaque opaque;
int32 cmpval;
/*
* When nextkey = false (normal case): if the scan key that brought us to
* this page is > the high key stored on the page, then the page has split
* and we need to move right. (If the scan key is equal to the high key,
* we might or might not need to move right; have to scan the page first
* anyway.)
*
* When nextkey = true: move right if the scan key is >= page's high key.
*
* The page could even have split more than once, so scan as far as
* needed.
*
* We also have to move right if we followed a link that brought us to a
* dead page.
*/
cmpval = nextkey ? 0 : 1;
for (;;)
{
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_RIGHTMOST(opaque))
break;
/*
* Finish any incomplete splits we encounter along the way.
*/
if (forupdate && P_INCOMPLETE_SPLIT(opaque))
{
BlockNumber blkno = BufferGetBlockNumber(buf);
/* upgrade our lock if necessary */
if (access == BT_READ)
{
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBuffer(buf, BT_WRITE);
}
if (P_INCOMPLETE_SPLIT(opaque))
_bt_finish_split(rel, buf, stack);
else
_bt_relbuf(rel, buf);
/* re-acquire the lock in the right mode, and re-check */
buf = _bt_getbuf(rel, blkno, access);
continue;
}
if (P_IGNORE(opaque) || _bt_compare(rel, keysz, scankey, page, P_HIKEY) >= cmpval)
{
/* step right one page */
buf = _bt_relandgetbuf(rel, buf, opaque->btpo_next, access);
continue;
}
else
break;
}
if (P_IGNORE(opaque))
elog(ERROR, "fell off the end of index \"%s\"",
RelationGetRelationName(rel));
return buf;
}
/*
* _bt_walk_left() -- step left one page, if possible
*
* The given buffer must be pinned and read-locked. This will be dropped
* before stepping left. On return, we have pin and read lock on the
* returned page, instead.
*
* Returns InvalidBuffer if there is no page to the left (no lock is held
* in that case).
*
* When working on a non-leaf level, it is possible for the returned page
* to be half-dead; the caller should check that condition and step left
* again if it's important.
*/
static Buffer
_bt_walk_left(Relation rel, Buffer buf)
{
Page page;
BTPageOpaque opaque;
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
for (;;)
{
BlockNumber obknum;
BlockNumber lblkno;
BlockNumber blkno;
int tries;
/* if we're at end of tree, release buf and return failure */
if (P_LEFTMOST(opaque))
{
_bt_relbuf(rel, buf);
break;
}
/* remember original page we are stepping left from */
obknum = BufferGetBlockNumber(buf);
/* step left */
blkno = lblkno = opaque->btpo_prev;
_bt_relbuf(rel, buf);
/* check for interrupts while we're not holding any buffer lock */
CHECK_FOR_INTERRUPTS();
buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* If this isn't the page we want, walk right till we find what we
* want --- but go no more than four hops (an arbitrary limit). If we
* don't find the correct page by then, the most likely bet is that
* the original page got deleted and isn't in the sibling chain at all
* anymore, not that its left sibling got split more than four times.
*
* Note that it is correct to test P_ISDELETED not P_IGNORE here,
* because half-dead pages are still in the sibling chain. Caller
* must reject half-dead pages if wanted.
*/
tries = 0;
for (;;)
{
if (!P_ISDELETED(opaque) && opaque->btpo_next == obknum)
{
/* Found desired page, return it */
return buf;
}
if (P_RIGHTMOST(opaque) || ++tries > 4)
break;
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/* Return to the original page to see what's up */
buf = _bt_relandgetbuf(rel, buf, obknum, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISDELETED(opaque))
{
/*
* It was deleted. Move right to first nondeleted page (there
* must be one); that is the page that has acquired the deleted
* one's keyspace, so stepping left from it will take us where we
* want to be.
*/
for (;;)
{
if (P_RIGHTMOST(opaque))
elog(ERROR, "fell off the end of index \"%s\"",
RelationGetRelationName(rel));
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_ISDELETED(opaque))
break;
}
/*
* Now return to top of loop, resetting obknum to point to this
* nondeleted page, and try again.
*/
}
else
{
/*
* It wasn't deleted; the explanation had better be that the page
* to the left got split or deleted. Without this check, we'd go
* into an infinite loop if there's anything wrong.
*/
if (opaque->btpo_prev == lblkno)
elog(ERROR, "could not find left sibling of block %u in index \"%s\"",
obknum, RelationGetRelationName(rel));
/* Okay to try again with new lblkno value */
}
}
return InvalidBuffer;
}
/*
* _bt_steppage() -- Step to next page containing valid data for scan
*
* On entry, so->currPos.buf must be pinned and read-locked. We'll drop
* the lock and pin before moving to next page.
*
* On success exit, we hold pin and read-lock on the next interesting page,
* and so->currPos is updated to contain data from that page.
*
* If there are no more matching records in the given direction, we drop all
* locks and pins, set so->currPos.buf to InvalidBuffer, and return FALSE.
*/
static bool
_bt_steppage(IndexScanDesc scan, ScanDirection dir)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Relation rel;
Page page;
BTPageOpaque opaque;
/* we must have the buffer pinned and locked */
Assert(BufferIsValid(so->currPos.buf));
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, true);
/*
* Before we modify currPos, make a copy of the page data if there was a
* mark position that needs it.
*/
if (so->markItemIndex >= 0)
{
/* bump pin on current buffer for assignment to mark buffer */
IncrBufferRefCount(so->currPos.buf);
memcpy(&so->markPos, &so->currPos,
offsetof(BTScanPosData, items[1]) +
so->currPos.lastItem * sizeof(BTScanPosItem));
if (so->markTuples)
memcpy(so->markTuples, so->currTuples,
so->currPos.nextTupleOffset);
so->markPos.itemIndex = so->markItemIndex;
so->markItemIndex = -1;
}
rel = scan->indexRelation;
if (ScanDirectionIsForward(dir))
{
/* Walk right to the next page with data */
/* We must rely on the previously saved nextPage link! */
BlockNumber blkno = so->currPos.nextPage;
/* Remember we left a page with data */
so->currPos.moreLeft = true;
for (;;)
{
/* release the previous buffer */
_bt_relbuf(rel, so->currPos.buf);
so->currPos.buf = InvalidBuffer;
/* if we're at end of scan, give up */
if (blkno == P_NONE || !so->currPos.moreRight)
return false;
/* check for interrupts while we're not holding any buffer lock */
CHECK_FOR_INTERRUPTS();
/* step right one page */
so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
/* check for deleted page */
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
PredicateLockPage(rel, blkno, scan->xs_snapshot);
/* see if there are any matches on this page */
/* note that this will clear moreRight if we can stop */
if (_bt_readpage(scan, dir, P_FIRSTDATAKEY(opaque)))
break;
}
/* nope, keep going */
blkno = opaque->btpo_next;
}
}
else
{
/* Remember we left a page with data */
so->currPos.moreRight = true;
/*
* Walk left to the next page with data. This is much more complex
* than the walk-right case because of the possibility that the page
* to our left splits while we are in flight to it, plus the
* possibility that the page we were on gets deleted after we leave
* it. See nbtree/README for details.
*/
for (;;)
{
/* Done if we know there are no matching keys to the left */
if (!so->currPos.moreLeft)
{
_bt_relbuf(rel, so->currPos.buf);
so->currPos.buf = InvalidBuffer;
return false;
}
/* Step to next physical page */
so->currPos.buf = _bt_walk_left(rel, so->currPos.buf);
/* if we're physically at end of index, return failure */
if (so->currPos.buf == InvalidBuffer)
return false;
/*
* Okay, we managed to move left to a non-deleted page. Done if
* it's not half-dead and contains matching tuples. Else loop back
* and do it all again.
*/
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
PredicateLockPage(rel, BufferGetBlockNumber(so->currPos.buf), scan->xs_snapshot);
/* see if there are any matches on this page */
/* note that this will clear moreLeft if we can stop */
if (_bt_readpage(scan, dir, PageGetMaxOffsetNumber(page)))
break;
}
}
}
return true;
}
/*
* _bt_step() -- Step one item in the requested direction in a scan on
* the tree.
*
* *bufP is the current buffer (read-locked and pinned). If we change
* pages, it's updated appropriately.
*
* If successful, update scan's currentItemData and return true.
* If no adjacent record exists in the requested direction,
* release buffer pin/locks and return false.
*/
bool
_bt_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir)
{
Relation rel = scan->indexRelation;
ItemPointer current = &(scan->currentItemData);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Page page;
BTPageOpaque opaque;
OffsetNumber offnum,
maxoff;
BlockNumber blkno;
/*
* Don't use ItemPointerGetOffsetNumber or you risk to get assertion
* due to ability of ip_posid to be equal 0.
*/
offnum = current->ip_posid;
page = BufferGetPage(*bufP);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
maxoff = PageGetMaxOffsetNumber(page);
if (ScanDirectionIsForward(dir))
{
if (!PageIsEmpty(page) && offnum < maxoff)
offnum = OffsetNumberNext(offnum);
else
{
/* Walk right to the next page with data */
for (;;)
{
/* if we're at end of scan, release the buffer and return */
if (P_RIGHTMOST(opaque))
{
_bt_relbuf(rel, *bufP);
ItemPointerSetInvalid(current);
*bufP = so->btso_curbuf = InvalidBuffer;
return false;
}
/* step right one page */
blkno = opaque->btpo_next;
_bt_relbuf(rel, *bufP);
*bufP = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(*bufP);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
maxoff = PageGetMaxOffsetNumber(page);
/* done if it's not empty */
offnum = P_FIRSTDATAKEY(opaque);
if (!PageIsEmpty(page) && offnum <= maxoff)
break;
}
}
}
}
else
/* backwards scan */
{
if (offnum > P_FIRSTDATAKEY(opaque))
offnum = OffsetNumberPrev(offnum);
else
{
/*
* Walk left to the next page with data. This is much more
* complex than the walk-right case because of the possibility
* that the page to our left splits while we are in flight to
* it, plus the possibility that the page we were on gets
* deleted after we leave it. See nbtree/README for details.
*/
for (;;)
{
*bufP = _bt_walk_left(rel, *bufP);
/* if we're at end of scan, return failure */
if (*bufP == InvalidBuffer)
{
ItemPointerSetInvalid(current);
so->btso_curbuf = InvalidBuffer;
return false;
}
page = BufferGetPage(*bufP);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* Okay, we managed to move left to a non-deleted page.
* Done if it's not half-dead and not empty. Else loop
* back and do it all again.
*/
if (!P_IGNORE(opaque))
{
maxoff = PageGetMaxOffsetNumber(page);
offnum = maxoff;
if (!PageIsEmpty(page) &&
maxoff >= P_FIRSTDATAKEY(opaque))
break;
}
}
}
}
/* Update scan state */
so->btso_curbuf = *bufP;
blkno = BufferGetBlockNumber(*bufP);
ItemPointerSet(current, blkno, offnum);
return true;
}
/*
* _bt_search() -- Search the tree for a particular scankey,
* or more precisely for the first leaf page it could be on.
*
* Return value is a stack of parent-page pointers. *bufP is set to the
* address of the leaf-page buffer, which is read-locked and pinned.
* No locks are held on the parent pages, however!
*
* NOTE that the returned buffer is read-locked regardless of the access
* parameter. However, access = BT_WRITE will allow an empty root page
* to be created and returned. When access = BT_READ, an empty index
* will result in *bufP being set to InvalidBuffer.
*/
BTStack
_bt_search(Relation rel, int keysz, ScanKey scankey,
Buffer *bufP, int access)
{
BTStack stack_in = NULL;
/* Get the root page to start with */
*bufP = _bt_getroot(rel, access);
/* If index is empty and access = BT_READ, no root page is created. */
if (!BufferIsValid(*bufP))
return (BTStack) NULL;
/* Loop iterates once per level descended in the tree */
for (;;)
{
Page page;
BTPageOpaque opaque;
OffsetNumber offnum;
ItemId itemid;
BTItem btitem;
IndexTuple itup;
BlockNumber blkno;
BlockNumber par_blkno;
BTStack new_stack;
/*
* Race -- the page we just grabbed may have split since we read
* its pointer in the parent (or metapage). If it has, we may
* need to move right to its new sibling. Do that.
*/
*bufP = _bt_moveright(rel, *bufP, keysz, scankey, BT_READ);
/* if this is a leaf page, we're done */
page = BufferGetPage(*bufP);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISLEAF(opaque))
break;
/*
* Find the appropriate item on the internal page, and get the
* child page that it points to.
*/
offnum = _bt_binsrch(rel, *bufP, keysz, scankey);
itemid = PageGetItemId(page, offnum);
btitem = (BTItem) PageGetItem(page, itemid);
itup = &(btitem->bti_itup);
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
par_blkno = BufferGetBlockNumber(*bufP);
/*
* We need to save the location of the index entry we chose in the
* parent page on a stack. In case we split the tree, we'll use
* the stack to work back up to the parent page. We also save the
* actual downlink (TID) to uniquely identify the index entry, in
* case it moves right while we're working lower in the tree. See
* the paper by Lehman and Yao for how this is detected and
* handled. (We use the child link to disambiguate duplicate keys
* in the index -- Lehman and Yao disallow duplicate keys.)
*/
new_stack = (BTStack) palloc(sizeof(BTStackData));
new_stack->bts_blkno = par_blkno;
new_stack->bts_offset = offnum;
memcpy(&new_stack->bts_btitem, btitem, sizeof(BTItemData));
new_stack->bts_parent = stack_in;
/* drop the read lock on the parent page, acquire one on the child */
_bt_relbuf(rel, *bufP);
*bufP = _bt_getbuf(rel, blkno, BT_READ);
/* okay, all set to move down a level */
stack_in = new_stack;
}
return stack_in;
}
/*
* _bt_get_endpoint() -- Find the first or last page on a given tree level
*
* If the index is empty, we will return InvalidBuffer; any other failure
* condition causes ereport(). We will not return a dead page.
*
* The returned buffer is pinned and read-locked.
*/
Buffer
_bt_get_endpoint(Relation rel, uint32 level, bool rightmost)
{
Buffer buf;
Page page;
BTPageOpaque opaque;
OffsetNumber offnum;
BlockNumber blkno;
BTItem btitem;
IndexTuple itup;
/*
* If we are looking for a leaf page, okay to descend from fast root;
* otherwise better descend from true root. (There is no point in
* being smarter about intermediate levels.)
*/
if (level == 0)
buf = _bt_getroot(rel, BT_READ);
else
buf = _bt_gettrueroot(rel);
if (!BufferIsValid(buf))
{
/* empty index... */
return InvalidBuffer;
}
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
for (;;)
{
/*
* If we landed on a deleted page, step right to find a live page
* (there must be one). Also, if we want the rightmost page, step
* right if needed to get to it (this could happen if the page
* split since we obtained a pointer to it).
*/
while (P_IGNORE(opaque) ||
(rightmost && !P_RIGHTMOST(opaque)))
{
blkno = opaque->btpo_next;
if (blkno == P_NONE)
elog(ERROR, "fell off the end of \"%s\"",
RelationGetRelationName(rel));
_bt_relbuf(rel, buf);
buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/* Done? */
if (opaque->btpo.level == level)
break;
if (opaque->btpo.level < level)
elog(ERROR, "btree level %u not found", level);
/* Descend to leftmost or rightmost child page */
if (rightmost)
offnum = PageGetMaxOffsetNumber(page);
else
offnum = P_FIRSTDATAKEY(opaque);
btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
itup = &(btitem->bti_itup);
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
_bt_relbuf(rel, buf);
buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
return buf;
}
/*
* _bt_pagedel() -- Delete a page from the b-tree.
*
* 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 read-locked. This lock and
* pin will be dropped before exiting.
*
* Returns the number of pages successfully deleted (zero on failure; could
* be more than one if parent blocks were deleted).
*
* 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, bool vacuum_full)
{
BlockNumber target,
leftsib,
rightsib,
parent;
OffsetNumber poffset,
maxoff;
uint32 targetlevel,
ilevel;
ItemId itemid;
BTItem targetkey,
btitem;
ScanKey itup_scankey;
BTStack stack;
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;
/*
* 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))
{
_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 = CopyBTItem((BTItem) PageGetItem(page, itemid));
/*
* We need to get an approximate pointer to the page's parent page. 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). To avoid deadlocks, we'd
* better drop the target page lock first.
*/
_bt_relbuf(rel, buf);
/* we need a scan key to do our search, so build one */
itup_scankey = _bt_mkscankey(rel, &(targetkey->bti_itup));
/* 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++;
}
/*
* 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 \"%s\"",
target, RelationGetRelationName(rel));
/*
* And next write-lock the (current) right sibling.
*/
rightsib = opaque->btpo_next;
rbuf = _bt_getbuf(rel, rightsib, BT_WRITE);
/*
* Next find and write-lock the current parent of the target page. This is
* essentially the same as the corresponding step of splitting. However,
* it's possible for the search to fail (for reasons explained in README).
* If that happens, we recover by searching the whole parent level, which
* is a tad inefficient but doesn't happen often enough to be a problem.
*/
ItemPointerSet(&(stack->bts_btitem.bti_itup.t_tid),
target, P_HIKEY);
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
{
/* Find the leftmost page in the parent level */
pbuf = _bt_get_endpoint(rel, opaque->btpo.level + 1, false);
stack->bts_blkno = BufferGetBlockNumber(pbuf);
stack->bts_offset = InvalidOffsetNumber;
_bt_relbuf(rel, pbuf);
/* and repeat search from there */
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
elog(ERROR, "failed to re-find parent key in \"%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.
*/
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
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, rbuf);
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
}
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 can safely acquire a lock on the metapage here --- see comments for
* _bt_newroot().
*/
if (leftsib == P_NONE)
{
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;
}
}
}
/*
* 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.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (parent_half_dead)
{
PageIndexTupleDelete(page, poffset);
opaque->btpo_flags |= BTP_HALF_DEAD;
}
else
{
OffsetNumber nextoffset;
itemid = PageGetItemId(page, poffset);
btitem = (BTItem) PageGetItem(page, itemid);
Assert(ItemPointerGetBlockNumber(&(btitem->bti_itup.t_tid)) == target);
ItemPointerSet(&(btitem->bti_itup.t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
/* This part is just for double-checking */
itemid = PageGetItemId(page, nextoffset);
btitem = (BTItem) PageGetItem(page, itemid);
if (ItemPointerGetBlockNumber(&(btitem->bti_itup.t_tid)) != rightsib)
elog(PANIC, "right sibling is not next child in \"%s\"",
RelationGetRelationName(rel));
PageIndexTupleDelete(page, nextoffset);
}
/*
* Update siblings' side-links. Note the target page's side-links will
* continue to point to the siblings.
*/
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_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;
}
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete_page xlrec;
xl_btree_metadata xlmeta;
uint8 xlinfo;
XLogRecPtr recptr;
XLogRecData rdata[5];
XLogRecData *nextrdata;
xlrec.target.node = rel->rd_node;
ItemPointerSet(&(xlrec.target.tid), 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
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();
/* Write and release buffers */
if (BufferIsValid(metabuf))
_bt_wrtbuf(rel, metabuf);
_bt_wrtbuf(rel, pbuf);
_bt_wrtbuf(rel, rbuf);
_bt_wrtbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_wrtbuf(rel, lbuf);
/*
* If parent became half dead, recurse to try 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.)
*/
if (parent_half_dead)
{
buf = _bt_getbuf(rel, parent, BT_READ);
return _bt_pagedel(rel, buf, vacuum_full) + 1;
}
if (parent_one_child && rightsib_empty)
{
buf = _bt_getbuf(rel, rightsib, BT_READ);
return _bt_pagedel(rel, buf, vacuum_full) + 1;
}
return 1;
}
/*
* _bt_gettrueroot() -- Get the true root page of the btree.
*
* This is the same as the BT_READ case of _bt_getroot(), except
* we follow the true-root link not the fast-root link.
*
* By the time we acquire lock on the root page, it might have been split and
* not be the true root anymore. This is okay for the present uses of this
* routine; we only really need to be able to move up at least one tree level
* from whatever non-root page we were at. If we ever do need to lock the
* one true root page, we could loop here, re-reading the metapage on each
* failure. (Note that it wouldn't do to hold the lock on the metapage while
* moving to the root --- that'd deadlock against any concurrent root split.)
*/
Buffer
_bt_gettrueroot(Relation rel)
{
Buffer metabuf;
Page metapg;
BTPageOpaque metaopaque;
Buffer rootbuf;
Page rootpage;
BTPageOpaque rootopaque;
BlockNumber rootblkno;
uint32 rootlevel;
BTMetaPageData *metad;
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_READ);
metapg = BufferGetPage(metabuf);
metaopaque = (BTPageOpaque) PageGetSpecialPointer(metapg);
metad = BTPageGetMeta(metapg);
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, fail */
if (metad->btm_root == P_NONE)
{
_bt_relbuf(rel, metabuf);
return InvalidBuffer;
}
rootblkno = metad->btm_root;
rootlevel = metad->btm_level;
/*
* 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 \"%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 \"%s\" has level %u, expected %u",
rootblkno, RelationGetRelationName(rel),
rootopaque->btpo.level, rootlevel);
return rootbuf;
}
/*
* _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;
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;
}
/* 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);
_bt_pageinit(rootpage, BufferGetPageSize(rootbuf));
rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
rootopaque->btpo_prev = rootopaque->btpo_next = P_NONE;
rootopaque->btpo_flags = (BTP_LEAF | BTP_ROOT);
rootopaque->btpo.level = 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;
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_newroot xlrec;
XLogRecPtr recptr;
XLogRecData rdata;
xlrec.node = rel->rd_node;
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();
_bt_wrtnorelbuf(rel, rootbuf);
/*
* 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, write and release it */
_bt_wrtbuf(rel, metabuf);
}
else
{
rootblkno = metad->btm_fastroot;
Assert(rootblkno != P_NONE);
rootlevel = metad->btm_fastlevel;
/*
* 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 \"%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 \"%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;
}
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);
}
