/*
* _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_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;
}
/*
* pgstat_btree_page -- check tuples in a btree page
*/
static void
pgstat_btree_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno,
BufferAccessStrategy bstrategy)
{
Buffer buf;
Page page;
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
LockBuffer(buf, BT_READ);
page = BufferGetPage(buf);
/* Page is valid, see what to do with it */
if (PageIsNew(page))
{
/* fully empty page */
stat->free_space += BLCKSZ;
}
else
{
BTPageOpaque opaque;
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_IGNORE(opaque))
{
/* recyclable page */
stat->free_space += BLCKSZ;
}
else if (P_ISLEAF(opaque))
{
pgstat_index_page(stat, page, P_FIRSTDATAKEY(opaque),
PageGetMaxOffsetNumber(page));
}
else
{
/* root or node */
}
}
_bt_relbuf(rel, 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_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_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;
}
static Datum
pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo)
{
Datum result;
BlockNumber nblocks;
BlockNumber blkno;
BTIndexStat indexStat;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
/*
* Read metapage
*/
{
Buffer buffer = ReadBufferExtended(rel, MAIN_FORKNUM, 0, RBM_NORMAL, bstrategy);
Page page = BufferGetPage(buffer);
BTMetaPageData *metad = BTPageGetMeta(page);
indexStat.version = metad->btm_version;
indexStat.level = metad->btm_level;
indexStat.root_blkno = metad->btm_root;
ReleaseBuffer(buffer);
}
/* -- init counters -- */
indexStat.internal_pages = 0;
indexStat.leaf_pages = 0;
indexStat.empty_pages = 0;
indexStat.deleted_pages = 0;
indexStat.max_avail = 0;
indexStat.free_space = 0;
indexStat.fragments = 0;
/*
* Scan all blocks except the metapage
*/
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buffer;
Page page;
BTPageOpaque opaque;
CHECK_FOR_INTERRUPTS();
/* Read and lock buffer */
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/* Determine page type, and update totals */
if (P_ISDELETED(opaque))
indexStat.deleted_pages++;
else if (P_IGNORE(opaque))
indexStat.empty_pages++; /* this is the "half dead" state */
else if (P_ISLEAF(opaque))
{
int max_avail;
max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
indexStat.max_avail += max_avail;
indexStat.free_space += PageGetFreeSpace(page);
indexStat.leaf_pages++;
/*
* If the next leaf is on an earlier block, it means a
* fragmentation.
*/
if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
indexStat.fragments++;
}
else
indexStat.internal_pages++;
/* Unlock and release buffer */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
relation_close(rel, AccessShareLock);
/*----------------------------
* Build a result tuple
*----------------------------
*/
{
TupleDesc tupleDesc;
int j;
char *values[10];
HeapTuple tuple;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
j = 0;
values[j++] = psprintf("%d", indexStat.version);
values[j++] = psprintf("%d", indexStat.level);
values[j++] = psprintf(INT64_FORMAT,
(1 + /* include the metapage in index_size */
indexStat.leaf_pages +
indexStat.internal_pages +
indexStat.deleted_pages +
indexStat.empty_pages) * BLCKSZ);
values[j++] = psprintf("%u", indexStat.root_blkno);
values[j++] = psprintf(INT64_FORMAT, indexStat.internal_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.leaf_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.empty_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.deleted_pages);
if (indexStat.max_avail > 0)
values[j++] = psprintf("%.2f",
100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
else
values[j++] = pstrdup("NaN");
if (indexStat.leaf_pages > 0)
values[j++] = psprintf("%.2f",
(double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
else
values[j++] = pstrdup("NaN");
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
values);
result = HeapTupleGetDatum(tuple);
}
return result;
}
/**
* @brief Read the left-most leaf page by walking down on index tree structure
* from root node.
*
* Process flow
* -# Open index file and read meta page
* -# Get block number of root page
* -# Read "fast root" page
* -# Read left child page until reaching left-most leaf page
*
* After calling this function, the members of BTReader are the following:
* - smgr : Smgr relation of the existing index file.
* - blkno : block number of left-most leaf page. If there is no leaf page,
* InvalidBlockNumber is set.
* - offnum : InvalidOffsetNumber is set.
* - page : Left-most leaf page, or undefined if no leaf page.
*
* @param reader [in/out] B-Tree index reader
* @return true iff there are some tuples
*/
static bool
BTReaderInit(BTReader *reader, Relation rel)
{
BTPageOpaque metaopaque;
BTMetaPageData *metad;
BTPageOpaque opaque;
BlockNumber blkno;
/*
* HACK: We cannot use smgropen because smgrs returned from it
* will be closed automatically when we assign a new file node.
*
* XXX: It might be better to open the previous relfilenode with
* smgropen *after* RelationSetNewRelfilenode.
*/
memset(&reader->smgr, 0, sizeof(reader->smgr));
#if PG_VERSION_NUM >= 90100
reader->smgr.smgr_rnode.node = rel->rd_node;
reader->smgr.smgr_rnode.backend =
rel->rd_backend == MyBackendId ? MyBackendId : InvalidBackendId;
#else
reader->smgr.smgr_rnode = rel->rd_node;
#endif
reader->smgr.smgr_which = 0; /* md.c */
reader->blkno = InvalidBlockNumber;
reader->offnum = InvalidOffsetNumber;
reader->page = palloc(BLCKSZ);
/*
* Read meta page and check sanity of it.
*
* XXX: It might be better to do REINDEX against corrupted indexes
* instead of raising errors because we've spent long time for data
* loading...
*/
BTReaderReadPage(reader, BTREE_METAPAGE);
metaopaque = (BTPageOpaque) PageGetSpecialPointer(reader->page);
metad = BTPageGetMeta(reader->page);
if (!(metaopaque->btpo_flags & BTP_META) ||
metad->btm_magic != BTREE_MAGIC)
ereport(ERROR,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("index \"%s\" is not a reader",
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 (metad->btm_root == P_NONE)
{
/* No root page; We ignore the index in the subsequent build. */
reader->blkno = InvalidBlockNumber;
return false;
}
/* Go to the fast root page. */
blkno = metad->btm_fastroot;
BTReaderReadPage(reader, blkno);
opaque = (BTPageOpaque) PageGetSpecialPointer(reader->page);
/* Walk down to the left-most leaf page */
while (!P_ISLEAF(opaque))
{
ItemId firstid;
IndexTuple itup;
/* Get the block number of the left child */
firstid = PageGetItemId(reader->page, P_FIRSTDATAKEY(opaque));
itup = (IndexTuple) PageGetItem(reader->page, firstid);
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
/* Go down to children */
for (;;)
{
BTReaderReadPage(reader, blkno);
opaque = (BTPageOpaque) PageGetSpecialPointer(reader->page);
if (!P_IGNORE(opaque))
break;
if (P_RIGHTMOST(opaque))
{
/* We reach end of the index without any valid leaves. */
reader->blkno = InvalidBlockNumber;
return false;
}
blkno = opaque->btpo_next;
}
}
return true;
}
/* -------------------------------------------------
* GetBTPageStatistics()
*
* Collect statistics of single b-tree page
* -------------------------------------------------
*/
static void
GetBTPageStatistics(block_t blkno, buf_id_t buffer, BTPageStat *stat)
{
page_p page = BUF_PAGE(buffer);
struct page_hdr * phdr = (struct page_hdr *) page;
item_id_t maxoff = PAGE_MAX_ITEM_ID(page);
struct bt_page_opaque * opaque = (struct bt_page_opaque *) PAGE_SPECIAL_PTR(page);
int item_size = 0;
int off;
stat->blkno = blkno;
stat->max_avail = BLK_SZ - (BLK_SZ - phdr->pd_special + PAGE_HDR_SZ);
stat->dead_items = stat->live_items = 0;
stat->page_size = PAGE_SZ(page);
/* page type (flags) */
if (P_ISDELETED(opaque))
{
stat->type = 'd';
stat->btpo.xact = opaque->btpo.xact;
return;
}
else if (P_IGNORE(opaque))
stat->type = 'e';
else if (P_ISLEAF(opaque))
stat->type = 'l';
else if (P_ISROOT(opaque))
stat->type = 'r';
else
stat->type = 'i';
/* btpage opaque data */
stat->btpo_prev = opaque->btpo_prev;
stat->btpo_next = opaque->btpo_next;
stat->btpo.level = opaque->btpo.level;
stat->btpo_flags = opaque->btpo_flags;
stat->btpo_cycleid = opaque->btpo_cycleid;
/* count live and dead tuples, and free space */
for (off = FIRST_ITEM_ID; off <= maxoff; off++)
{
struct index_tuple * itup;
struct item_id * id = PAGE_ITEM_ID(page, off);
itup = (struct index_tuple *) PAGE_GET_ITEM(page, id);
item_size += INDEX_TUPLE_SZ(itup);
if (!ITEMID_DEAD(id))
stat->live_items++;
else
stat->dead_items++;
}
stat->free_size = page_free_space(page);
if ((stat->live_items + stat->dead_items) > 0)
stat->avg_item_size = item_size / (stat->live_items + stat->dead_items);
else
stat->avg_item_size = 0;
}
/* -------------------------------------------------
* GetBTPageStatistics()
*
* Collect statistics of single b-tree page
* -------------------------------------------------
*/
static void
GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat)
{
Page page = BufferGetPage(buffer);
PageHeader phdr = (PageHeader) page;
OffsetNumber maxoff = PageGetMaxOffsetNumber(page);
BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page);
int item_size = 0;
int off;
stat->blkno = blkno;
stat->max_avail = BLCKSZ - (BLCKSZ - phdr->pd_special + SizeOfPageHeaderData);
stat->dead_items = stat->live_items = 0;
stat->page_size = PageGetPageSize(page);
/* page type (flags) */
if (P_ISDELETED(opaque))
{
stat->type = 'd';
stat->btpo.xact = opaque->btpo.xact;
return;
}
else if (P_IGNORE(opaque))
stat->type = 'e';
else if (P_ISLEAF(opaque))
stat->type = 'l';
else if (P_ISROOT(opaque))
stat->type = 'r';
else
stat->type = 'i';
/* btpage opaque data */
stat->btpo_prev = opaque->btpo_prev;
stat->btpo_next = opaque->btpo_next;
stat->btpo.level = opaque->btpo.level;
stat->btpo_flags = opaque->btpo_flags;
stat->btpo_cycleid = opaque->btpo_cycleid;
/* count live and dead tuples, and free space */
for (off = FirstOffsetNumber; off <= maxoff; off++)
{
IndexTuple itup;
ItemId id = PageGetItemId(page, off);
itup = (IndexTuple) PageGetItem(page, id);
item_size += IndexTupleSize(itup);
if (!ItemIdIsDead(id))
stat->live_items++;
else
stat->dead_items++;
}
stat->free_size = PageGetFreeSpace(page);
if ((stat->live_items + stat->dead_items) > 0)
stat->avg_item_size = item_size / (stat->live_items + stat->dead_items);
else
stat->avg_item_size = 0;
}
/*
* _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;
}
/*
* btvacuumpage --- VACUUM one page
*
* This processes a single page for btvacuumscan(). In some cases we
* must go back and re-examine previously-scanned pages; this routine
* recurses when necessary to handle that case.
*
* blkno is the page to process. orig_blkno is the highest block number
* reached by the outer btvacuumscan loop (the same as blkno, unless we
* are recursing to re-examine a previous page).
*/
static void
btvacuumpage(BTVacState *vstate, BlockNumber blkno, BlockNumber orig_blkno)
{
MIRROREDLOCK_BUFMGR_DECLARE;
IndexVacuumInfo *info = vstate->info;
IndexBulkDeleteResult *stats = vstate->stats;
IndexBulkDeleteCallback callback = vstate->callback;
void *callback_state = vstate->callback_state;
Relation rel = info->index;
bool delete_now;
BlockNumber recurse_to;
Buffer buf;
Page page;
BTPageOpaque opaque;
restart:
delete_now = false;
recurse_to = P_NONE;
/* call vacuum_delay_point while not holding any buffer lock */
vacuum_delay_point();
/*
* We can't use _bt_getbuf() here because it always applies
* _bt_checkpage(), which will barf on an all-zero page. We want to
* recycle all-zero pages, not fail. Also, we want to use a nondefault
* buffer access strategy.
*/
// -------- MirroredLock ----------
MIRROREDLOCK_BUFMGR_LOCK;
buf = ReadBufferWithStrategy(rel, blkno, info->strategy);
LockBuffer(buf, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!PageIsNew(page))
_bt_checkpage(rel, buf);
/*
* If we are recursing, the only case we want to do anything with is a
* live leaf page having the current vacuum cycle ID. Any other state
* implies we already saw the page (eg, deleted it as being empty). In
* particular, we don't want to risk adding it to freePages twice.
*/
if (blkno != orig_blkno)
{
if (_bt_page_recyclable(page) ||
P_IGNORE(opaque) ||
!P_ISLEAF(opaque) ||
opaque->btpo_cycleid != vstate->cycleid)
{
_bt_relbuf(rel, buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return;
}
}
/* Page is valid, see what to do with it */
if (_bt_page_recyclable(page))
{
/* Okay to recycle this page */
if (vstate->nFreePages < vstate->maxFreePages)
vstate->freePages[vstate->nFreePages++] = blkno;
vstate->totFreePages++;
stats->pages_deleted++;
}
else if (P_ISDELETED(opaque))
{
/* Already deleted, but can't recycle yet */
stats->pages_deleted++;
}
else if (P_ISHALFDEAD(opaque))
{
/* Half-dead, try to delete */
delete_now = true;
}
else if (P_ISLEAF(opaque))
{
OffsetNumber deletable[MaxOffsetNumber];
int ndeletable;
OffsetNumber offnum,
minoff,
maxoff;
/*
* Trade in the initial read lock for a super-exclusive write lock on
* this page. We must get such a lock on every leaf page over the
* course of the vacuum scan, whether or not it actually contains any
* deletable tuples --- see nbtree/README.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBufferForCleanup(buf);
/*
* Check whether we need to recurse back to earlier pages. What we
* are concerned about is a page split that happened since we started
* the vacuum scan. If the split moved some tuples to a lower page
* then we might have missed 'em. If so, set up for tail recursion.
* (Must do this before possibly clearing btpo_cycleid below!)
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid &&
!(opaque->btpo_flags & BTP_SPLIT_END) &&
!P_RIGHTMOST(opaque) &&
opaque->btpo_next < orig_blkno)
recurse_to = opaque->btpo_next;
/*
* Scan over all items to see which ones need deleted according to the
* callback function.
*/
ndeletable = 0;
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
if (callback)
{
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
IndexTuple itup;
ItemPointer htup;
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
htup = &(itup->t_tid);
if (callback(htup, callback_state))
deletable[ndeletable++] = offnum;
}
}
/*
* Apply any needed deletes. We issue just one _bt_delitems() call
* per page, so as to minimize WAL traffic.
*/
if (ndeletable > 0)
{
_bt_delitems(rel, buf, deletable, ndeletable, true);
stats->tuples_removed += ndeletable;
/* must recompute maxoff */
maxoff = PageGetMaxOffsetNumber(page);
}
else
{
/*
* If the page has been split during this vacuum cycle, it seems
* worth expending a write to clear btpo_cycleid even if we don't
* have any deletions to do. (If we do, _bt_delitems takes care
* of this.) This ensures we won't process the page again.
*
* We treat this like a hint-bit update because there's no need to
* WAL-log it.
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid)
{
opaque->btpo_cycleid = 0;
SetBufferCommitInfoNeedsSave(buf);
}
}
/*
* If it's now empty, try to delete; else count the live tuples. We
* don't delete when recursing, though, to avoid putting entries into
* freePages out-of-order (doesn't seem worth any extra code to handle
* the case).
*/
if (minoff > maxoff)
delete_now = (blkno == orig_blkno);
else
stats->num_index_tuples += maxoff - minoff + 1;
}
if (delete_now)
{
MemoryContext oldcontext;
int ndel;
/* Run pagedel in a temp context to avoid memory leakage */
MemoryContextReset(vstate->pagedelcontext);
oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);
ndel = _bt_pagedel(rel, buf, NULL, info->vacuum_full);
/* count only this page, else may double-count parent */
if (ndel)
stats->pages_deleted++;
/*
* During VACUUM FULL it's okay to recycle deleted pages immediately,
* since there can be no other transactions scanning the index. Note
* that we will only recycle the current page and not any parent pages
* that _bt_pagedel might have recursed to; this seems reasonable in
* the name of simplicity. (Trying to do otherwise would mean we'd
* have to sort the list of recyclable pages we're building.)
*/
if (ndel && info->vacuum_full)
{
if (vstate->nFreePages < vstate->maxFreePages)
vstate->freePages[vstate->nFreePages++] = blkno;
vstate->totFreePages++;
}
MemoryContextSwitchTo(oldcontext);
/* pagedel released buffer, so we shouldn't */
}
else
_bt_relbuf(rel, buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
/*
* This is really tail recursion, but if the compiler is too stupid to
* optimize it as such, we'd eat an uncomfortably large amount of stack
* space per recursion level (due to the deletable[] array). A failure is
* improbable since the number of levels isn't likely to be large ... but
* just in case, let's hand-optimize into a loop.
*/
if (recurse_to != P_NONE)
{
blkno = recurse_to;
goto restart;
}
}
/*
* btvacuumpage --- VACUUM one page
*
* This processes a single page for btvacuumscan(). In some cases we
* must go back and re-examine previously-scanned pages; this routine
* recurses when necessary to handle that case.
*
* blkno is the page to process. orig_blkno is the highest block number
* reached by the outer btvacuumscan loop (the same as blkno, unless we
* are recursing to re-examine a previous page).
*/
static void
btvacuumpage(BTVacState *vstate, BlockNumber blkno, BlockNumber orig_blkno)
{
IndexVacuumInfo *info = vstate->info;
IndexBulkDeleteResult *stats = vstate->stats;
IndexBulkDeleteCallback callback = vstate->callback;
void *callback_state = vstate->callback_state;
Relation rel = info->index;
bool delete_now;
BlockNumber recurse_to;
Buffer buf;
Page page;
BTPageOpaque opaque = NULL;
restart:
delete_now = false;
recurse_to = P_NONE;
/* call vacuum_delay_point while not holding any buffer lock */
vacuum_delay_point();
/*
* We can't use _bt_getbuf() here because it always applies
* _bt_checkpage(), which will barf on an all-zero page. We want to
* recycle all-zero pages, not fail. Also, we want to use a nondefault
* buffer access strategy.
*/
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
info->strategy);
LockBuffer(buf, BT_READ);
page = BufferGetPage(buf);
if (!PageIsNew(page))
{
_bt_checkpage(rel, buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/*
* If we are recursing, the only case we want to do anything with is a
* live leaf page having the current vacuum cycle ID. Any other state
* implies we already saw the page (eg, deleted it as being empty).
*/
if (blkno != orig_blkno)
{
if (_bt_page_recyclable(page) ||
P_IGNORE(opaque) ||
!P_ISLEAF(opaque) ||
opaque->btpo_cycleid != vstate->cycleid)
{
_bt_relbuf(rel, buf);
return;
}
}
/* Page is valid, see what to do with it */
if (_bt_page_recyclable(page))
{
/* Okay to recycle this page */
RecordFreeIndexPage(rel, blkno);
vstate->totFreePages++;
stats->pages_deleted++;
}
else if (P_ISDELETED(opaque))
{
/* Already deleted, but can't recycle yet */
stats->pages_deleted++;
}
else if (P_ISHALFDEAD(opaque))
{
/* Half-dead, try to delete */
delete_now = true;
}
else if (P_ISLEAF(opaque))
{
OffsetNumber deletable[MaxOffsetNumber];
int ndeletable;
OffsetNumber offnum,
minoff,
maxoff;
/*
* Trade in the initial read lock for a super-exclusive write lock on
* this page. We must get such a lock on every leaf page over the
* course of the vacuum scan, whether or not it actually contains any
* deletable tuples --- see nbtree/README.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBufferForCleanup(buf);
/*
* Remember highest leaf page number we've taken cleanup lock on; see
* notes in btvacuumscan
*/
if (blkno > vstate->lastBlockLocked)
vstate->lastBlockLocked = blkno;
/*
* Check whether we need to recurse back to earlier pages. What we
* are concerned about is a page split that happened since we started
* the vacuum scan. If the split moved some tuples to a lower page
* then we might have missed 'em. If so, set up for tail recursion.
* (Must do this before possibly clearing btpo_cycleid below!)
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid &&
!(opaque->btpo_flags & BTP_SPLIT_END) &&
!P_RIGHTMOST(opaque) &&
opaque->btpo_next < orig_blkno)
recurse_to = opaque->btpo_next;
/*
* Scan over all items to see which ones need deleted according to the
* callback function.
*/
ndeletable = 0;
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
if (callback)
{
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
IndexTuple itup;
ItemPointer htup;
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
htup = &(itup->t_tid);
/*
* During Hot Standby we currently assume that
* XLOG_BTREE_VACUUM records do not produce conflicts. That is
* only true as long as the callback function depends only
* upon whether the index tuple refers to heap tuples removed
* in the initial heap scan. When vacuum starts it derives a
* value of OldestXmin. Backends taking later snapshots could
* have a RecentGlobalXmin with a later xid than the vacuum's
* OldestXmin, so it is possible that row versions deleted
* after OldestXmin could be marked as killed by other
* backends. The callback function *could* look at the index
* tuple state in isolation and decide to delete the index
* tuple, though currently it does not. If it ever did, we
* would need to reconsider whether XLOG_BTREE_VACUUM records
* should cause conflicts. If they did cause conflicts they
* would be fairly harsh conflicts, since we haven't yet
* worked out a way to pass a useful value for
* latestRemovedXid on the XLOG_BTREE_VACUUM records. This
* applies to *any* type of index that marks index tuples as
* killed.
*/
if (callback(htup, callback_state))
deletable[ndeletable++] = offnum;
}
}
/*
* Apply any needed deletes. We issue just one _bt_delitems_vacuum()
* call per page, so as to minimize WAL traffic.
*/
if (ndeletable > 0)
{
/*
* Notice that the issued XLOG_BTREE_VACUUM WAL record includes
* all information to the replay code to allow it to get a cleanup
* lock on all pages between the previous lastBlockVacuumed and
* this page. This ensures that WAL replay locks all leaf pages at
* some point, which is important should non-MVCC scans be
* requested. This is currently unused on standby, but we record
* it anyway, so that the WAL contains the required information.
*
* Since we can visit leaf pages out-of-order when recursing,
* replay might end up locking such pages an extra time, but it
* doesn't seem worth the amount of bookkeeping it'd take to avoid
* that.
*/
_bt_delitems_vacuum(rel, buf, deletable, ndeletable,
vstate->lastBlockVacuumed);
/*
* Remember highest leaf page number we've issued a
* XLOG_BTREE_VACUUM WAL record for.
*/
if (blkno > vstate->lastBlockVacuumed)
vstate->lastBlockVacuumed = blkno;
stats->tuples_removed += ndeletable;
/* must recompute maxoff */
maxoff = PageGetMaxOffsetNumber(page);
}
else
{
/*
* If the page has been split during this vacuum cycle, it seems
* worth expending a write to clear btpo_cycleid even if we don't
* have any deletions to do. (If we do, _bt_delitems_vacuum takes
* care of this.) This ensures we won't process the page again.
*
* We treat this like a hint-bit update because there's no need to
* WAL-log it.
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid)
{
opaque->btpo_cycleid = 0;
MarkBufferDirtyHint(buf, true);
}
}
/*
* If it's now empty, try to delete; else count the live tuples. We
* don't delete when recursing, though, to avoid putting entries into
* freePages out-of-order (doesn't seem worth any extra code to handle
* the case).
*/
if (minoff > maxoff)
delete_now = (blkno == orig_blkno);
else
stats->num_index_tuples += maxoff - minoff + 1;
}
if (delete_now)
{
MemoryContext oldcontext;
int ndel;
/* Run pagedel in a temp context to avoid memory leakage */
MemoryContextReset(vstate->pagedelcontext);
oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);
ndel = _bt_pagedel(rel, buf);
/* count only this page, else may double-count parent */
if (ndel)
stats->pages_deleted++;
MemoryContextSwitchTo(oldcontext);
/* pagedel released buffer, so we shouldn't */
}
else
_bt_relbuf(rel, buf);
/*
* This is really tail recursion, but if the compiler is too stupid to
* optimize it as such, we'd eat an uncomfortably large amount of stack
* space per recursion level (due to the deletable[] array). A failure is
* improbable since the number of levels isn't likely to be large ... but
* just in case, let's hand-optimize into a loop.
*/
if (recurse_to != P_NONE)
{
blkno = recurse_to;
goto restart;
}
}
/* ------------------------------------------------------
* pgstatindex()
*
* Usage: SELECT * FROM pgstatindex('t1_pkey');
* ------------------------------------------------------
*/
Datum
pgstatindex(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_P(0);
Relation rel;
RangeVar *relrv;
Datum result;
BlockNumber nblocks;
BlockNumber blkno;
BTIndexStat indexStat;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pgstattuple functions"))));
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
/*
* Read metapage
*/
{
Buffer buffer = ReadBuffer(rel, 0);
Page page = BufferGetPage(buffer);
BTMetaPageData *metad = BTPageGetMeta(page);
indexStat.version = metad->btm_version;
indexStat.level = metad->btm_level;
indexStat.root_blkno = metad->btm_root;
ReleaseBuffer(buffer);
}
/* -- init counters -- */
indexStat.root_pages = 0;
indexStat.internal_pages = 0;
indexStat.leaf_pages = 0;
indexStat.empty_pages = 0;
indexStat.deleted_pages = 0;
indexStat.max_avail = 0;
indexStat.free_space = 0;
indexStat.fragments = 0;
/*
* Scan all blocks except the metapage
*/
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buffer;
Page page;
BTPageOpaque opaque;
/* Read and lock buffer */
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/* Determine page type, and update totals */
if (P_ISLEAF(opaque))
{
int max_avail;
max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
indexStat.max_avail += max_avail;
indexStat.free_space += PageGetFreeSpace(page);
indexStat.leaf_pages++;
/*
* If the next leaf is on an earlier block, it means a
* fragmentation.
*/
if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
indexStat.fragments++;
}
else if (P_ISDELETED(opaque))
indexStat.deleted_pages++;
else if (P_IGNORE(opaque))
indexStat.empty_pages++;
else if (P_ISROOT(opaque))
indexStat.root_pages++;
else
indexStat.internal_pages++;
/* Unlock and release buffer */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
relation_close(rel, AccessShareLock);
/*----------------------------
* Build a result tuple
*----------------------------
*/
{
TupleDesc tupleDesc;
int j;
char *values[10];
HeapTuple tuple;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
j = 0;
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", indexStat.version);
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", indexStat.level);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT,
(indexStat.root_pages +
indexStat.leaf_pages +
indexStat.internal_pages +
indexStat.deleted_pages +
indexStat.empty_pages) * BLCKSZ);
values[j] = palloc(32);
snprintf(values[j++], 32, "%u", indexStat.root_blkno);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.internal_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.leaf_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.empty_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.deleted_pages);
values[j] = palloc(32);
if (indexStat.max_avail > 0)
snprintf(values[j++], 32, "%.2f",
100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
else
snprintf(values[j++], 32, "NaN");
values[j] = palloc(32);
if (indexStat.leaf_pages > 0)
snprintf(values[j++], 32, "%.2f",
(double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
else
snprintf(values[j++], 32, "NaN");
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
values);
result = HeapTupleGetDatum(tuple);
}
PG_RETURN_DATUM(result);
}
