/*
* _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.
*
* 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,
int access)
{
Page page;
BTPageOpaque opaque;
int32 cmpval;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* 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;
while (!P_RIGHTMOST(opaque) &&
(P_IGNORE(opaque) ||
_bt_compare(rel, keysz, scankey, page, P_HIKEY) >= cmpval))
{
/* step right one page */
BlockNumber rblkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, rblkno, access);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
if (P_IGNORE(opaque))
elog(ERROR, "fell off the end of index \"%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_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_search() -- Search the tree for a particular scankey,
* or more precisely for the first leaf page it could be on.
*
* 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.
*
* 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. Also, in BT_WRITE mode,
* any incomplete splits encountered during the search will be finished.
*/
BTStack
_bt_search(Relation rel, int keysz, ScanKey scankey, bool nextkey,
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;
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.
*
* In write-mode, allow _bt_moveright to finish any incomplete splits
* along the way. Strictly speaking, we'd only need to finish an
* incomplete split on the leaf page we're about to insert to, not on
* any of the upper levels (they is taken care of in _bt_getstackbuf,
* if the leaf page is split and we insert to the parent page). But
* this is a good opportunity to finish splits of internal pages too.
*/
*bufP = _bt_moveright(rel, *bufP, keysz, scankey, nextkey,
(access == BT_WRITE), stack_in,
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, nextkey);
itemid = PageGetItemId(page, offnum);
itup = (IndexTuple) PageGetItem(page, itemid);
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_btentry, itup, sizeof(IndexTupleData));
new_stack->bts_parent = stack_in;
/* drop the read lock on the parent page, acquire one on the child */
*bufP = _bt_relandgetbuf(rel, *bufP, blkno, BT_READ);
/* okay, all set to move down a level */
stack_in = new_stack;
}
return stack_in;
}
/*
* _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_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;
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))
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 index \"%s\"",
RelationGetRelationName(rel));
buf = _bt_relandgetbuf(rel, buf, 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 in index \"%s\"",
level, RelationGetRelationName(rel));
/* Descend to leftmost or rightmost child page */
if (rightmost)
offnum = PageGetMaxOffsetNumber(page);
else
offnum = P_FIRSTDATAKEY(opaque);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
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_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;
}
/*
* _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;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
/* 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));
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 (;;)
{
/* if we're at end of scan, release the buffer and return */
if (blkno == P_NONE || !so->currPos.moreRight)
{
_bt_relbuf(rel, so->currPos.buf);
so->currPos.buf = InvalidBuffer;
return false;
}
/* step right one page */
so->currPos.buf = _bt_relandgetbuf(rel, so->currPos.buf,
blkno, BT_READ);
/* check for deleted page */
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
/* 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))
{
/* 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;
}
