/*
* _bt_initmetapage() -- Fill a page buffer with a correct metapage image
*/
void
_bt_initmetapage(Page page, BlockNumber rootbknum, uint32 level)
{
BTMetaPageData *metad;
BTPageOpaque metaopaque;
_bt_pageinit(page, BLCKSZ);
metad = BTPageGetMeta(page);
metad->btm_magic = BTREE_MAGIC;
metad->btm_version = BTREE_VERSION;
metad->btm_root = rootbknum;
metad->btm_level = level;
metad->btm_fastroot = rootbknum;
metad->btm_fastlevel = level;
metaopaque = (BTPageOpaque) PageGetSpecialPointer(page);
metaopaque->btpo_flags = BTP_META;
/*
* Set pd_lower just past the end of the metadata. This is not essential
* but it makes the page look compressible to xlog.c.
*/
((PageHeader) page)->pd_lower =
((char *) metad + sizeof(BTMetaPageData)) - (char *) page;
}
static void
_bt_restore_meta(XLogReaderState *record, uint8 block_id)
{
XLogRecPtr lsn = record->EndRecPtr;
Buffer metabuf;
Page metapg;
BTMetaPageData *md;
BTPageOpaque pageop;
xl_btree_metadata *xlrec;
char *ptr;
Size len;
metabuf = XLogInitBufferForRedo(record, block_id);
ptr = XLogRecGetBlockData(record, block_id, &len);
Assert(len == sizeof(xl_btree_metadata));
Assert(BufferGetBlockNumber(metabuf) == BTREE_METAPAGE);
xlrec = (xl_btree_metadata *) ptr;
metapg = BufferGetPage(metabuf);
_bt_pageinit(metapg, BufferGetPageSize(metabuf));
md = BTPageGetMeta(metapg);
md->btm_magic = BTREE_MAGIC;
md->btm_version = BTREE_VERSION;
md->btm_root = xlrec->root;
md->btm_level = xlrec->level;
md->btm_fastroot = xlrec->fastroot;
md->btm_fastlevel = xlrec->fastlevel;
pageop = (BTPageOpaque) PageGetSpecialPointer(metapg);
pageop->btpo_flags = BTP_META;
/*
* Set pd_lower just past the end of the metadata. This is not essential
* but it makes the page look compressible to xlog.c.
*/
((PageHeader) metapg)->pd_lower =
((char *) md + sizeof(BTMetaPageData)) - (char *) metapg;
PageSetLSN(metapg, lsn);
MarkBufferDirty(metabuf);
UnlockReleaseBuffer(metabuf);
}
static void
btree_xlog_newroot(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_newroot *xlrec = (xl_btree_newroot *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque pageop;
char *ptr;
Size len;
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_flags = BTP_ROOT;
pageop->btpo_prev = pageop->btpo_next = P_NONE;
pageop->btpo.level = xlrec->level;
if (xlrec->level == 0)
pageop->btpo_flags |= BTP_LEAF;
pageop->btpo_cycleid = 0;
if (xlrec->level > 0)
{
ptr = XLogRecGetBlockData(record, 0, &len);
_bt_restore_page(page, ptr, len);
/* Clear the incomplete-split flag in left child */
_bt_clear_incomplete_split(record, 1);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
_bt_restore_meta(record, 2);
}
/*
* allocate workspace for a new, clean btree page, not linked to any siblings.
*/
static Page
_bt_blnewpage(uint32 level)
{
Page page;
BTPageOpaque opaque;
page = (Page) palloc(BLCKSZ);
/* Zero the page and set up standard page header info */
_bt_pageinit(page, BLCKSZ);
/* Initialize BT opaque state */
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_prev = opaque->btpo_next = P_NONE;
opaque->btpo.level = level;
opaque->btpo_flags = (level > 0) ? 0 : BTP_LEAF;
opaque->btpo_cycleid = 0;
/* Make the P_HIKEY line pointer appear allocated */
((PageHeader) page)->pd_lower += sizeof(ItemIdData);
return page;
}
/*
* _bt_getbuf() -- Get a buffer by block number for read or write.
*
* blkno == P_NEW means to get an unallocated index page. The page
* will be initialized before returning it.
*
* When this routine returns, the appropriate lock is set on the
* requested buffer and its reference count has been incremented
* (ie, the buffer is "locked and pinned"). Also, we apply
* _bt_checkpage to sanity-check the page (except in P_NEW case).
*/
Buffer
_bt_getbuf(Relation rel, BlockNumber blkno, int access)
{
Buffer buf;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
if (blkno != P_NEW)
{
/* Read an existing block of the relation */
buf = ReadBuffer(rel, blkno);
LockBuffer(buf, access);
_bt_checkpage(rel, buf);
}
else
{
bool needLock;
Page page;
Assert(access == BT_WRITE);
/*
* First see if the FSM knows of any free pages.
*
* We can't trust the FSM's report unreservedly; we have to check that
* the page is still free. (For example, an already-free page could
* have been re-used between the time the last VACUUM scanned it and
* the time the VACUUM made its FSM updates.)
*
* In fact, it's worse than that: we can't even assume that it's safe
* to take a lock on the reported page. If somebody else has a lock
* on it, or even worse our own caller does, we could deadlock. (The
* own-caller scenario is actually not improbable. Consider an index
* on a serial or timestamp column. Nearly all splits will be at the
* rightmost page, so it's entirely likely that _bt_split will call us
* while holding a lock on the page most recently acquired from FSM. A
* VACUUM running concurrently with the previous split could well have
* placed that page back in FSM.)
*
* To get around that, we ask for only a conditional lock on the
* reported page. If we fail, then someone else is using the page,
* and we may reasonably assume it's not free. (If we happen to be
* wrong, the worst consequence is the page will be lost to use till
* the next VACUUM, which is no big problem.)
*/
for (;;)
{
blkno = GetFreeIndexPage(&rel->rd_node);
if (blkno == InvalidBlockNumber)
break;
buf = ReadBuffer(rel, blkno);
if (ConditionalLockBuffer(buf))
{
page = BufferGetPage(buf);
if (_bt_page_recyclable(page))
{
/* Okay to use page. Re-initialize and return it */
_bt_pageinit(page, BufferGetPageSize(buf));
return buf;
}
elog(DEBUG2, "FSM returned nonrecyclable page");
_bt_relbuf(rel, buf);
}
else
{
elog(DEBUG2, "FSM returned nonlockable page");
/* couldn't get lock, so just drop pin */
ReleaseBuffer(buf);
}
}
/*
* Extend the relation by one page.
*
* We have to use a lock to ensure no one else is extending the rel at
* the same time, else we will both try to initialize the same new
* page. We can skip locking for new or temp relations, however,
* since no one else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
buf = ReadBuffer(rel, P_NEW);
/* Acquire buffer lock on new page */
LockBuffer(buf, BT_WRITE);
/*
* Release the file-extension lock; it's now OK for someone else to
* extend the relation some more. Note that we cannot release this
* lock before we have buffer lock on the new page, or we risk a race
* condition against btvacuumscan --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Initialize the new page before returning it */
page = BufferGetPage(buf);
Assert(PageIsNew((PageHeader) page));
_bt_pageinit(page, BufferGetPageSize(buf));
}
/* ref count and lock type are correct */
return buf;
}
static void
btree_xlog_unlink_page(uint8 info, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_unlink_page *xlrec = (xl_btree_unlink_page *) XLogRecGetData(record);
BlockNumber leftsib;
BlockNumber rightsib;
Buffer buffer;
Page page;
BTPageOpaque pageop;
leftsib = xlrec->leftsib;
rightsib = xlrec->rightsib;
/*
* In normal operation, we would lock all the pages this WAL record
* touches before changing any of them. In WAL replay, it should be okay
* to lock just one page at a time, since no concurrent index updates can
* be happening, and readers should not care whether they arrive at the
* target page or not (since it's surely empty).
*/
/* Fix left-link of right sibling */
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = leftsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Fix right-link of left sibling, if any */
if (leftsib != P_NONE)
{
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_next = rightsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/* Rewrite target page as empty deleted page */
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = leftsib;
pageop->btpo_next = rightsib;
pageop->btpo.xact = xlrec->btpo_xact;
pageop->btpo_flags = BTP_DELETED;
pageop->btpo_cycleid = 0;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
/*
* If we deleted a parent of the targeted leaf page, instead of the leaf
* itself, update the leaf to point to the next remaining child in the
* branch.
*/
if (XLogRecHasBlockRef(record, 3))
{
/*
* There is no real data on the page, so we just re-create it from
* scratch using the information from the WAL record.
*/
IndexTupleData trunctuple;
buffer = XLogInitBufferForRedo(record, 3);
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
pageop->btpo_prev = xlrec->leafleftsib;
pageop->btpo_next = xlrec->leafrightsib;
pageop->btpo.level = 0;
pageop->btpo_cycleid = 0;
/* Add a dummy hikey item */
MemSet(&trunctuple, 0, sizeof(IndexTupleData));
trunctuple.t_info = sizeof(IndexTupleData);
if (xlrec->topparent != InvalidBlockNumber)
ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
else
ItemPointerSetInvalid(&trunctuple.t_tid);
if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
false, false) == InvalidOffsetNumber)
elog(ERROR, "could not add dummy high key to half-dead page");
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/* Update metapage if needed */
if (info == XLOG_BTREE_UNLINK_PAGE_META)
_bt_restore_meta(record, 4);
}
static void
btree_xlog_mark_page_halfdead(uint8 info, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_mark_page_halfdead *xlrec = (xl_btree_mark_page_halfdead *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque pageop;
IndexTupleData trunctuple;
/*
* In normal operation, we would lock all the pages this WAL record
* touches before changing any of them. In WAL replay, it should be okay
* to lock just one page at a time, since no concurrent index updates can
* be happening, and readers should not care whether they arrive at the
* target page or not (since it's surely empty).
*/
/* parent page */
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
OffsetNumber poffset;
ItemId itemid;
IndexTuple itup;
OffsetNumber nextoffset;
BlockNumber rightsib;
page = (Page) BufferGetPage(buffer);
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
poffset = xlrec->poffset;
nextoffset = OffsetNumberNext(poffset);
itemid = PageGetItemId(page, nextoffset);
itup = (IndexTuple) PageGetItem(page, itemid);
rightsib = ItemPointerGetBlockNumber(&itup->t_tid);
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
PageIndexTupleDelete(page, nextoffset);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Rewrite the leaf page as a halfdead page */
buffer = XLogInitBufferForRedo(record, 0);
page = (Page) BufferGetPage(buffer);
_bt_pageinit(page, BufferGetPageSize(buffer));
pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = xlrec->leftblk;
pageop->btpo_next = xlrec->rightblk;
pageop->btpo.level = 0;
pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
pageop->btpo_cycleid = 0;
/*
* Construct a dummy hikey item that points to the next parent to be
* deleted (if any).
*/
MemSet(&trunctuple, 0, sizeof(IndexTupleData));
trunctuple.t_info = sizeof(IndexTupleData);
if (xlrec->topparent != InvalidBlockNumber)
ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
else
ItemPointerSetInvalid(&trunctuple.t_tid);
if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
false, false) == InvalidOffsetNumber)
elog(ERROR, "could not add dummy high key to half-dead page");
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
static void
btree_xlog_split(bool onleft, bool isroot, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record);
bool isleaf = (xlrec->level == 0);
Buffer lbuf;
Buffer rbuf;
Page rpage;
BTPageOpaque ropaque;
char *datapos;
Size datalen;
Item left_hikey = NULL;
Size left_hikeysz = 0;
BlockNumber leftsib;
BlockNumber rightsib;
BlockNumber rnext;
XLogRecGetBlockTag(record, 0, NULL, NULL, &leftsib);
XLogRecGetBlockTag(record, 1, NULL, NULL, &rightsib);
if (!XLogRecGetBlockTag(record, 2, NULL, NULL, &rnext))
rnext = P_NONE;
/*
* Clear the incomplete split flag on the left sibling of the child page
* this is a downlink for. (Like in btree_xlog_insert, this can be done
* before locking the other pages)
*/
if (!isleaf)
_bt_clear_incomplete_split(record, 3);
/* Reconstruct right (new) sibling page from scratch */
rbuf = XLogInitBufferForRedo(record, 1);
datapos = XLogRecGetBlockData(record, 1, &datalen);
rpage = (Page) BufferGetPage(rbuf);
_bt_pageinit(rpage, BufferGetPageSize(rbuf));
ropaque = (BTPageOpaque) PageGetSpecialPointer(rpage);
ropaque->btpo_prev = leftsib;
ropaque->btpo_next = rnext;
ropaque->btpo.level = xlrec->level;
ropaque->btpo_flags = isleaf ? BTP_LEAF : 0;
ropaque->btpo_cycleid = 0;
_bt_restore_page(rpage, datapos, datalen);
/*
* On leaf level, the high key of the left page is equal to the first key
* on the right page.
*/
if (isleaf)
{
ItemId hiItemId = PageGetItemId(rpage, P_FIRSTDATAKEY(ropaque));
left_hikey = PageGetItem(rpage, hiItemId);
left_hikeysz = ItemIdGetLength(hiItemId);
}
PageSetLSN(rpage, lsn);
MarkBufferDirty(rbuf);
/* don't release the buffer yet; we touch right page's first item below */
/* Now reconstruct left (original) sibling page */
if (XLogReadBufferForRedo(record, 0, &lbuf) == BLK_NEEDS_REDO)
{
/*
* To retain the same physical order of the tuples that they had, we
* initialize a temporary empty page for the left page and add all the
* items to that in item number order. This mirrors how _bt_split()
* works. It's not strictly required to retain the same physical
* order, as long as the items are in the correct item number order,
* but it helps debugging. See also _bt_restore_page(), which does
* the same for the right page.
*/
Page lpage = (Page) BufferGetPage(lbuf);
BTPageOpaque lopaque = (BTPageOpaque) PageGetSpecialPointer(lpage);
OffsetNumber off;
Item newitem = NULL;
Size newitemsz = 0;
Page newlpage;
OffsetNumber leftoff;
datapos = XLogRecGetBlockData(record, 0, &datalen);
if (onleft)
{
newitem = (Item) datapos;
newitemsz = MAXALIGN(IndexTupleSize(newitem));
datapos += newitemsz;
datalen -= newitemsz;
}
/* Extract left hikey and its size (assuming 16-bit alignment) */
if (!isleaf)
{
left_hikey = (Item) datapos;
left_hikeysz = MAXALIGN(IndexTupleSize(left_hikey));
datapos += left_hikeysz;
datalen -= left_hikeysz;
}
Assert(datalen == 0);
newlpage = PageGetTempPageCopySpecial(lpage);
/* Set high key */
leftoff = P_HIKEY;
if (PageAddItem(newlpage, left_hikey, left_hikeysz,
P_HIKEY, false, false) == InvalidOffsetNumber)
elog(PANIC, "failed to add high key to left page after split");
leftoff = OffsetNumberNext(leftoff);
for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstright; off++)
{
ItemId itemid;
Size itemsz;
Item item;
/* add the new item if it was inserted on left page */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
itemid = PageGetItemId(lpage, off);
itemsz = ItemIdGetLength(itemid);
item = PageGetItem(lpage, itemid);
if (PageAddItem(newlpage, item, itemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add old item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
/* cope with possibility that newitem goes at the end */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
PageRestoreTempPage(newlpage, lpage);
/* Fix opaque fields */
lopaque->btpo_flags = BTP_INCOMPLETE_SPLIT;
if (isleaf)
lopaque->btpo_flags |= BTP_LEAF;
lopaque->btpo_next = rightsib;
lopaque->btpo_cycleid = 0;
PageSetLSN(lpage, lsn);
MarkBufferDirty(lbuf);
}
/* We no longer need the buffers */
if (BufferIsValid(lbuf))
UnlockReleaseBuffer(lbuf);
UnlockReleaseBuffer(rbuf);
/*
* Fix left-link of the page to the right of the new right sibling.
*
* Note: in normal operation, we do this while still holding lock on the
* two split pages. However, that's not necessary for correctness in WAL
* replay, because no other index update can be in progress, and readers
* will cope properly when following an obsolete left-link.
*/
if (rnext != P_NONE)
{
Buffer buffer;
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buffer);
BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = rightsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
}
/*
* _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;
}
