/*
* Parse XLOG_HEAP_INSERT (not MULTI_INSERT!) records into tuplebufs.
*
* Deletes can contain the new tuple.
*/
static void
DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
xl_heap_insert *xlrec;
ReorderBufferChange *change;
RelFileNode target_node;
xlrec = (xl_heap_insert *) XLogRecGetData(r);
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_INSERT;
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
if (xlrec->flags & XLOG_HEAP_CONTAINS_NEW_TUPLE)
{
Size tuplelen;
char *tupledata = XLogRecGetBlockData(r, 0, &tuplelen);
change->data.tp.newtuple = ReorderBufferGetTupleBuf(ctx->reorder);
DecodeXLogTuple(tupledata, tuplelen, change->data.tp.newtuple);
}
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
/*
* Parse XLOG_HEAP_UPDATE and XLOG_HEAP_HOT_UPDATE, which have the same layout
* in the record, from wal into proper tuplebufs.
*
* Updates can possibly contain a new tuple and the old primary key.
*/
static void
DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
xl_heap_update *xlrec;
ReorderBufferChange *change;
char *data;
RelFileNode target_node;
xlrec = (xl_heap_update *) XLogRecGetData(r);
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
/* output plugin doesn't look for this origin, no need to queue */
if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
return;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_UPDATE;
change->origin_id = XLogRecGetOrigin(r);
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
if (xlrec->flags & XLH_UPDATE_CONTAINS_NEW_TUPLE)
{
Size datalen;
Size tuplelen;
data = XLogRecGetBlockData(r, 0, &datalen);
tuplelen = datalen - SizeOfHeapHeader;
change->data.tp.newtuple =
ReorderBufferGetTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.newtuple);
}
if (xlrec->flags & XLH_UPDATE_CONTAINS_OLD)
{
Size datalen;
Size tuplelen;
/* caution, remaining data in record is not aligned */
data = XLogRecGetData(r) + SizeOfHeapUpdate;
datalen = XLogRecGetDataLen(r) - SizeOfHeapUpdate;
tuplelen = datalen - SizeOfHeapHeader;
change->data.tp.oldtuple =
ReorderBufferGetTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.oldtuple);
}
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
/*
* Parse XLOG_HEAP_CONFIRM from wal into a confirmation change.
*
* This is pretty trivial, all the state essentially already setup by the
* speculative insertion.
*/
static void
DecodeSpecConfirm(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
ReorderBufferChange *change;
RelFileNode target_node;
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
/* output plugin doesn't look for this origin, no need to queue */
if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
return;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_INTERNAL_SPEC_CONFIRM;
change->origin_id = XLogRecGetOrigin(r);
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
static void
btree_xlog_delete(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_delete *xlrec = (xl_btree_delete *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque opaque;
/*
* If we have any conflict processing to do, it must happen before we
* update the page.
*
* Btree delete records can conflict with standby queries. You might
* think that vacuum records would conflict as well, but we've handled
* that already. XLOG_HEAP2_CLEANUP_INFO records provide the highest xid
* cleaned by the vacuum of the heap and so we can resolve any conflicts
* just once when that arrives. After that we know that no conflicts
* exist from individual btree vacuum records on that index.
*/
if (InHotStandby)
{
TransactionId latestRemovedXid = btree_xlog_delete_get_latestRemovedXid(record);
RelFileNode rnode;
XLogRecGetBlockTag(record, 0, &rnode, NULL, NULL);
ResolveRecoveryConflictWithSnapshot(latestRemovedXid, rnode);
}
/*
* We don't need to take a cleanup lock to apply these changes. See
* nbtree/README for details.
*/
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
if (XLogRecGetDataLen(record) > SizeOfBtreeDelete)
{
OffsetNumber *unused;
unused = (OffsetNumber *) ((char *) xlrec + SizeOfBtreeDelete);
PageIndexMultiDelete(page, unused, xlrec->nitems);
}
/*
* Mark the page as not containing any LP_DEAD items --- see comments
* in _bt_delitems_delete().
*/
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags &= ~BTP_HAS_GARBAGE;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/*
* Replay a revmap page extension
*/
static void
brin_xlog_revmap_extend(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_brin_revmap_extend *xlrec;
Buffer metabuf;
Buffer buf;
Page page;
BlockNumber targetBlk;
XLogRedoAction action;
xlrec = (xl_brin_revmap_extend *) XLogRecGetData(record);
XLogRecGetBlockTag(record, 1, NULL, NULL, &targetBlk);
Assert(xlrec->targetBlk == targetBlk);
/* Update the metapage */
action = XLogReadBufferForRedo(record, 0, &metabuf);
if (action == BLK_NEEDS_REDO)
{
Page metapg;
BrinMetaPageData *metadata;
metapg = BufferGetPage(metabuf);
metadata = (BrinMetaPageData *) PageGetContents(metapg);
Assert(metadata->lastRevmapPage == xlrec->targetBlk - 1);
metadata->lastRevmapPage = xlrec->targetBlk;
PageSetLSN(metapg, lsn);
/*
* Set pd_lower just past the end of the metadata. This is essential,
* because without doing so, metadata will be lost if xlog.c
* compresses the page. (We must do this here because pre-v11
* versions of PG did not set the metapage's pd_lower correctly, so a
* pg_upgraded index might contain the wrong value.)
*/
((PageHeader) metapg)->pd_lower =
((char *) metadata + sizeof(BrinMetaPageData)) - (char *) metapg;
MarkBufferDirty(metabuf);
}
/*
* Re-init the target block as a revmap page. There's never a full- page
* image here.
*/
buf = XLogInitBufferForRedo(record, 1);
page = (Page) BufferGetPage(buf);
brin_page_init(page, BRIN_PAGETYPE_REVMAP);
PageSetLSN(page, lsn);
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
if (BufferIsValid(metabuf))
UnlockReleaseBuffer(metabuf);
}
/*
* redo delete on gist index page to remove tuples marked as DEAD during index
* tuple insertion
*/
static void
gistRedoDeleteRecord(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
gistxlogDelete *xldata = (gistxlogDelete *) XLogRecGetData(record);
Buffer buffer;
Page page;
/*
* If we have any conflict processing to do, it must happen before we
* update the page.
*
* GiST delete records can conflict with standby queries. You might think
* that vacuum records would conflict as well, but we've handled that
* already. XLOG_HEAP2_CLEANUP_INFO records provide the highest xid
* cleaned by the vacuum of the heap and so we can resolve any conflicts
* just once when that arrives. After that we know that no conflicts
* exist from individual gist vacuum records on that index.
*/
if (InHotStandby)
{
TransactionId latestRemovedXid = gistRedoDeleteRecordGetLatestRemovedXid(record);
RelFileNode rnode;
XLogRecGetBlockTag(record, 0, &rnode, NULL, NULL);
ResolveRecoveryConflictWithSnapshot(latestRemovedXid, rnode);
}
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
page = (Page) BufferGetPage(buffer);
if (XLogRecGetDataLen(record) > SizeOfGistxlogDelete)
{
OffsetNumber *todelete;
todelete = (OffsetNumber *) ((char *) xldata + SizeOfGistxlogDelete);
PageIndexMultiDelete(page, todelete, xldata->ntodelete);
}
GistClearPageHasGarbage(page);
GistMarkTuplesDeleted(page);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/*
* Parse XLOG_HEAP_DELETE from wal into proper tuplebufs.
*
* Deletes can possibly contain the old primary key.
*/
static void
DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
xl_heap_delete *xlrec;
ReorderBufferChange *change;
RelFileNode target_node;
xlrec = (xl_heap_delete *) XLogRecGetData(r);
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
/*
* Super deletions are irrelevant for logical decoding, it's driven by the
* confirmation records.
*/
if (xlrec->flags & XLH_DELETE_IS_SUPER)
return;
/* output plugin doesn't look for this origin, no need to queue */
if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
return;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_DELETE;
change->origin_id = XLogRecGetOrigin(r);
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
/* old primary key stored */
if (xlrec->flags & XLH_DELETE_CONTAINS_OLD)
{
Size datalen = XLogRecGetDataLen(r) - SizeOfHeapDelete;
Size tuplelen = datalen - SizeOfHeapHeader;
Assert(XLogRecGetDataLen(r) > (SizeOfHeapDelete + SizeOfHeapHeader));
change->data.tp.oldtuple =
ReorderBufferGetTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple((char *) xlrec + SizeOfHeapDelete,
datalen, change->data.tp.oldtuple);
}
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
/*
* Parse XLOG_HEAP_INSERT (not MULTI_INSERT!) records into tuplebufs.
*
* Deletes can contain the new tuple.
*/
static void
DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
Size datalen;
char *tupledata;
Size tuplelen;
XLogReaderState *r = buf->record;
xl_heap_insert *xlrec;
ReorderBufferChange *change;
RelFileNode target_node;
xlrec = (xl_heap_insert *) XLogRecGetData(r);
/*
* Ignore insert records without new tuples (this does happen when
* raw_heap_insert marks the TOAST record as HEAP_INSERT_NO_LOGICAL).
*/
if (!(xlrec->flags & XLH_INSERT_CONTAINS_NEW_TUPLE))
return;
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
/* output plugin doesn't look for this origin, no need to queue */
if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
return;
change = ReorderBufferGetChange(ctx->reorder);
if (!(xlrec->flags & XLH_INSERT_IS_SPECULATIVE))
change->action = REORDER_BUFFER_CHANGE_INSERT;
else
change->action = REORDER_BUFFER_CHANGE_INTERNAL_SPEC_INSERT;
change->origin_id = XLogRecGetOrigin(r);
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
tupledata = XLogRecGetBlockData(r, 0, &datalen);
tuplelen = datalen - SizeOfHeapHeader;
change->data.tp.newtuple =
ReorderBufferGetTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(tupledata, datalen, change->data.tp.newtuple);
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
/*
* Parse XLOG_HEAP_DELETE from wal into proper tuplebufs.
*
* Deletes can possibly contain the old primary key.
*/
static void
DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
xl_heap_delete *xlrec;
ReorderBufferChange *change;
RelFileNode target_node;
xlrec = (xl_heap_delete *) XLogRecGetData(r);
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &target_node, NULL, NULL);
if (target_node.dbNode != ctx->slot->data.database)
return;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_DELETE;
memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));
/* old primary key stored */
if (xlrec->flags & XLOG_HEAP_CONTAINS_OLD)
{
Assert(XLogRecGetDataLen(r) > (SizeOfHeapDelete + SizeOfHeapHeader));
change->data.tp.oldtuple = ReorderBufferGetTupleBuf(ctx->reorder);
DecodeXLogTuple((char *) xlrec + SizeOfHeapDelete,
XLogRecGetDataLen(r) - SizeOfHeapDelete,
change->data.tp.oldtuple);
}
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr, change);
}
static void
gistRedoPageSplitRecord(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
Buffer firstbuffer = InvalidBuffer;
Buffer buffer;
Page page;
int i;
bool isrootsplit = false;
/*
* We must hold lock on the first-listed page throughout the action,
* including while updating the left child page (if any). We can unlock
* remaining pages in the list as soon as they've been written, because
* there is no path for concurrent queries to reach those pages without
* first visiting the first-listed page.
*/
/* loop around all pages */
for (i = 0; i < xldata->npage; i++)
{
int flags;
char *data;
Size datalen;
int num;
BlockNumber blkno;
IndexTuple *tuples;
XLogRecGetBlockTag(record, i + 1, NULL, NULL, &blkno);
if (blkno == GIST_ROOT_BLKNO)
{
Assert(i == 0);
isrootsplit = true;
}
buffer = XLogInitBufferForRedo(record, i + 1);
page = (Page) BufferGetPage(buffer);
data = XLogRecGetBlockData(record, i + 1, &datalen);
tuples = decodePageSplitRecord(data, datalen, &num);
/* ok, clear buffer */
if (xldata->origleaf && blkno != GIST_ROOT_BLKNO)
flags = F_LEAF;
else
flags = 0;
GISTInitBuffer(buffer, flags);
/* and fill it */
gistfillbuffer(page, tuples, num, FirstOffsetNumber);
if (blkno == GIST_ROOT_BLKNO)
{
GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
GistPageSetNSN(page, xldata->orignsn);
GistClearFollowRight(page);
}
else
{
if (i < xldata->npage - 1)
{
BlockNumber nextblkno;
XLogRecGetBlockTag(record, i + 2, NULL, NULL, &nextblkno);
GistPageGetOpaque(page)->rightlink = nextblkno;
}
else
GistPageGetOpaque(page)->rightlink = xldata->origrlink;
GistPageSetNSN(page, xldata->orignsn);
if (i < xldata->npage - 1 && !isrootsplit &&
xldata->markfollowright)
GistMarkFollowRight(page);
else
GistClearFollowRight(page);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
if (i == 0)
firstbuffer = buffer;
else
UnlockReleaseBuffer(buffer);
}
/* Fix follow-right data on left child page, if any */
if (XLogRecHasBlockRef(record, 0))
gistRedoClearFollowRight(record, 0);
/* Finally, release lock on the first page */
UnlockReleaseBuffer(firstbuffer);
}
static void
spgRedoMoveLeafs(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
char *ptr = XLogRecGetData(record);
spgxlogMoveLeafs *xldata = (spgxlogMoveLeafs *) ptr;
SpGistState state;
OffsetNumber *toDelete;
OffsetNumber *toInsert;
int nInsert;
Buffer buffer;
Page page;
XLogRedoAction action;
BlockNumber blknoDst;
XLogRecGetBlockTag(record, 1, NULL, NULL, &blknoDst);
fillFakeState(&state, xldata->stateSrc);
nInsert = xldata->replaceDead ? 1 : xldata->nMoves + 1;
ptr += SizeOfSpgxlogMoveLeafs;
toDelete = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nMoves;
toInsert = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * nInsert;
/* now ptr points to the list of leaf tuples */
/*
* In normal operation we would have all three pages (source, dest, and
* parent) locked simultaneously; but in WAL replay it should be safe to
* update them one at a time, as long as we do it in the right order.
*/
/* Insert tuples on the dest page (do first, so redirect is valid) */
if (xldata->newPage)
{
buffer = XLogInitBufferForRedo(record, 1);
SpGistInitBuffer(buffer,
SPGIST_LEAF | (xldata->storesNulls ? SPGIST_NULLS : 0));
action = BLK_NEEDS_REDO;
}
else
action = XLogReadBufferForRedo(record, 1, &buffer);
if (action == BLK_NEEDS_REDO)
{
int i;
page = BufferGetPage(buffer);
for (i = 0; i < nInsert; i++)
{
char *leafTuple;
SpGistLeafTupleData leafTupleHdr;
/*
* the tuples are not aligned, so must copy to access the size
* field.
*/
leafTuple = ptr;
memcpy(&leafTupleHdr, leafTuple,
sizeof(SpGistLeafTupleData));
addOrReplaceTuple(page, (Item) leafTuple,
leafTupleHdr.size, toInsert[i]);
ptr += leafTupleHdr.size;
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Delete tuples from the source page, inserting a redirection pointer */
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
page = BufferGetPage(buffer);
spgPageIndexMultiDelete(&state, page, toDelete, xldata->nMoves,
state.isBuild ? SPGIST_PLACEHOLDER : SPGIST_REDIRECT,
SPGIST_PLACEHOLDER,
blknoDst,
toInsert[nInsert - 1]);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* And update the parent downlink */
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
SpGistInnerTuple tuple;
page = BufferGetPage(buffer);
tuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(tuple, xldata->nodeI,
blknoDst, toInsert[nInsert - 1]);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/*
* Get the latestRemovedXid from the heap pages pointed at by the index
* tuples being deleted. This puts the work for calculating latestRemovedXid
* into the recovery path rather than the primary path.
*
* It's possible that this generates a fair amount of I/O, since an index
* block may have hundreds of tuples being deleted. Repeat accesses to the
* same heap blocks are common, though are not yet optimised.
*
* XXX optimise later with something like XLogPrefetchBuffer()
*/
static TransactionId
btree_xlog_delete_get_latestRemovedXid(XLogReaderState *record)
{
xl_btree_delete *xlrec = (xl_btree_delete *) XLogRecGetData(record);
OffsetNumber *unused;
Buffer ibuffer,
hbuffer;
Page ipage,
hpage;
RelFileNode rnode;
BlockNumber blkno;
ItemId iitemid,
hitemid;
IndexTuple itup;
HeapTupleHeader htuphdr;
BlockNumber hblkno;
OffsetNumber hoffnum;
TransactionId latestRemovedXid = InvalidTransactionId;
int i;
/*
* If there's nothing running on the standby we don't need to derive a
* full latestRemovedXid value, so use a fast path out of here. This
* returns InvalidTransactionId, and so will conflict with all HS
* transactions; but since we just worked out that that's zero people,
* it's OK.
*
* XXX There is a race condition here, which is that a new backend might
* start just after we look. If so, it cannot need to conflict, but this
* coding will result in throwing a conflict anyway.
*/
if (CountDBBackends(InvalidOid) == 0)
return latestRemovedXid;
/*
* In what follows, we have to examine the previous state of the index
* page, as well as the heap page(s) it points to. This is only valid if
* WAL replay has reached a consistent database state; which means that
* the preceding check is not just an optimization, but is *necessary*. We
* won't have let in any user sessions before we reach consistency.
*/
if (!reachedConsistency)
elog(PANIC, "btree_xlog_delete_get_latestRemovedXid: cannot operate with inconsistent data");
/*
* Get index page. If the DB is consistent, this should not fail, nor
* should any of the heap page fetches below. If one does, we return
* InvalidTransactionId to cancel all HS transactions. That's probably
* overkill, but it's safe, and certainly better than panicking here.
*/
XLogRecGetBlockTag(record, 0, &rnode, NULL, &blkno);
ibuffer = XLogReadBufferExtended(rnode, MAIN_FORKNUM, blkno, RBM_NORMAL);
if (!BufferIsValid(ibuffer))
return InvalidTransactionId;
LockBuffer(ibuffer, BT_READ);
ipage = (Page) BufferGetPage(ibuffer);
/*
* Loop through the deleted index items to obtain the TransactionId from
* the heap items they point to.
*/
unused = (OffsetNumber *) ((char *) xlrec + SizeOfBtreeDelete);
for (i = 0; i < xlrec->nitems; i++)
{
/*
* Identify the index tuple about to be deleted
*/
iitemid = PageGetItemId(ipage, unused[i]);
itup = (IndexTuple) PageGetItem(ipage, iitemid);
/*
* Locate the heap page that the index tuple points at
*/
hblkno = ItemPointerGetBlockNumber(&(itup->t_tid));
hbuffer = XLogReadBufferExtended(xlrec->hnode, MAIN_FORKNUM, hblkno, RBM_NORMAL);
if (!BufferIsValid(hbuffer))
{
UnlockReleaseBuffer(ibuffer);
return InvalidTransactionId;
}
LockBuffer(hbuffer, BUFFER_LOCK_SHARE);
hpage = (Page) BufferGetPage(hbuffer);
/*
* Look up the heap tuple header that the index tuple points at by
* using the heap node supplied with the xlrec. We can't use
* heap_fetch, since it uses ReadBuffer rather than XLogReadBuffer.
* Note that we are not looking at tuple data here, just headers.
*/
hoffnum = ItemPointerGetOffsetNumber(&(itup->t_tid));
hitemid = PageGetItemId(hpage, hoffnum);
/*
* Follow any redirections until we find something useful.
*/
while (ItemIdIsRedirected(hitemid))
{
hoffnum = ItemIdGetRedirect(hitemid);
hitemid = PageGetItemId(hpage, hoffnum);
CHECK_FOR_INTERRUPTS();
}
/*
* If the heap item has storage, then read the header and use that to
* set latestRemovedXid.
*
* Some LP_DEAD items may not be accessible, so we ignore them.
*/
if (ItemIdHasStorage(hitemid))
{
htuphdr = (HeapTupleHeader) PageGetItem(hpage, hitemid);
HeapTupleHeaderAdvanceLatestRemovedXid(htuphdr, &latestRemovedXid);
}
else if (ItemIdIsDead(hitemid))
{
/*
* Conjecture: if hitemid is dead then it had xids before the xids
* marked on LP_NORMAL items. So we just ignore this item and move
* onto the next, for the purposes of calculating
* latestRemovedxids.
*/
}
else
Assert(!ItemIdIsUsed(hitemid));
UnlockReleaseBuffer(hbuffer);
}
UnlockReleaseBuffer(ibuffer);
/*
* If all heap tuples were LP_DEAD then we will be returning
* InvalidTransactionId here, which avoids conflicts. This matches
* existing logic which assumes that LP_DEAD tuples must already be older
* than the latestRemovedXid on the cleanup record that set them as
* LP_DEAD, hence must already have generated a conflict.
*/
return latestRemovedXid;
}
static void
btree_xlog_vacuum(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_vacuum *xlrec = (xl_btree_vacuum *) XLogRecGetData(record);
Buffer buffer;
Page page;
BTPageOpaque opaque;
/*
* If queries might be active then we need to ensure every leaf page is
* unpinned between the lastBlockVacuumed and the current block, if there
* are any. This prevents replay of the VACUUM from reaching the stage of
* removing heap tuples while there could still be indexscans "in flight"
* to those particular tuples (see nbtree/README).
*
* It might be worth checking if there are actually any backends running;
* if not, we could just skip this.
*
* Since VACUUM can visit leaf pages out-of-order, it might issue records
* with lastBlockVacuumed >= block; that's not an error, it just means
* nothing to do now.
*
* Note: since we touch all pages in the range, we will lock non-leaf
* pages, and also any empty (all-zero) pages that may be in the index. It
* doesn't seem worth the complexity to avoid that. But it's important
* that HotStandbyActiveInReplay() will not return true if the database
* isn't yet consistent; so we need not fear reading still-corrupt blocks
* here during crash recovery.
*/
if (HotStandbyActiveInReplay())
{
RelFileNode thisrnode;
BlockNumber thisblkno;
BlockNumber blkno;
XLogRecGetBlockTag(record, 0, &thisrnode, NULL, &thisblkno);
for (blkno = xlrec->lastBlockVacuumed + 1; blkno < thisblkno; blkno++)
{
/*
* We use RBM_NORMAL_NO_LOG mode because it's not an error
* condition to see all-zero pages. The original btvacuumpage
* scan would have skipped over all-zero pages, noting them in FSM
* but not bothering to initialize them just yet; so we mustn't
* throw an error here. (We could skip acquiring the cleanup lock
* if PageIsNew, but it's probably not worth the cycles to test.)
*
* XXX we don't actually need to read the block, we just need to
* confirm it is unpinned. If we had a special call into the
* buffer manager we could optimise this so that if the block is
* not in shared_buffers we confirm it as unpinned.
*/
buffer = XLogReadBufferExtended(thisrnode, MAIN_FORKNUM, blkno,
RBM_NORMAL_NO_LOG);
if (BufferIsValid(buffer))
{
LockBufferForCleanup(buffer);
UnlockReleaseBuffer(buffer);
}
}
}
/*
* Like in btvacuumpage(), we need to take a cleanup lock on every leaf
* page. See nbtree/README for details.
*/
if (XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, true, &buffer)
== BLK_NEEDS_REDO)
{
char *ptr;
Size len;
ptr = XLogRecGetBlockData(record, 0, &len);
page = (Page) BufferGetPage(buffer);
if (len > 0)
{
OffsetNumber *unused;
OffsetNumber *unend;
unused = (OffsetNumber *) ptr;
unend = (OffsetNumber *) ((char *) ptr + len);
if ((unend - unused) > 0)
PageIndexMultiDelete(page, unused, unend - unused);
}
/*
* Mark the page as not containing any LP_DEAD items --- see comments
* in _bt_delitems_vacuum().
*/
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags &= ~BTP_HAS_GARBAGE;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(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);
}
}
/*
* XLogReadBufferForRedoExtended
* Like XLogReadBufferForRedo, but with extra options.
*
* In RBM_ZERO_* modes, if the page doesn't exist, the relation is extended
* with all-zeroes pages up to the referenced block number. In
* RBM_ZERO_AND_LOCK and RBM_ZERO_AND_CLEANUP_LOCK modes, the return value
* is always BLK_NEEDS_REDO.
*
* (The RBM_ZERO_AND_CLEANUP_LOCK mode is redundant with the get_cleanup_lock
* parameter. Do not use an inconsistent combination!)
*
* If 'get_cleanup_lock' is true, a "cleanup lock" is acquired on the buffer
* using LockBufferForCleanup(), instead of a regular exclusive lock.
*/
XLogRedoAction
XLogReadBufferForRedoExtended(XLogReaderState *record,
uint8 block_id,
ReadBufferMode mode, bool get_cleanup_lock,
Buffer *buf)
{
XLogRecPtr lsn = record->EndRecPtr;
RelFileNode rnode;
ForkNumber forknum;
BlockNumber blkno;
Page page;
bool zeromode;
bool willinit;
if (!XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blkno))
{
/* Caller specified a bogus block_id */
elog(PANIC, "failed to locate backup block with ID %d", block_id);
}
/*
* Make sure that if the block is marked with WILL_INIT, the caller is
* going to initialize it. And vice versa.
*/
zeromode = (mode == RBM_ZERO_AND_LOCK || mode == RBM_ZERO_AND_CLEANUP_LOCK);
willinit = (record->blocks[block_id].flags & BKPBLOCK_WILL_INIT) != 0;
if (willinit && !zeromode)
elog(PANIC, "block with WILL_INIT flag in WAL record must be zeroed by redo routine");
if (!willinit && zeromode)
elog(PANIC, "block to be initialized in redo routine must be marked with WILL_INIT flag in the WAL record");
/* If it's a full-page image, restore it. */
if (XLogRecHasBlockImage(record, block_id))
{
*buf = XLogReadBufferExtended(rnode, forknum, blkno,
get_cleanup_lock ? RBM_ZERO_AND_CLEANUP_LOCK : RBM_ZERO_AND_LOCK);
page = BufferGetPage(*buf);
if (!RestoreBlockImage(record, block_id, page))
elog(ERROR, "failed to restore block image");
/*
* The page may be uninitialized. If so, we can't set the LSN because
* that would corrupt the page.
*/
if (!PageIsNew(page))
{
PageSetLSN(page, lsn);
}
MarkBufferDirty(*buf);
/*
* At the end of crash recovery the init forks of unlogged relations
* are copied, without going through shared buffers. So we need to
* force the on-disk state of init forks to always be in sync with the
* state in shared buffers.
*/
if (forknum == INIT_FORKNUM)
FlushOneBuffer(*buf);
return BLK_RESTORED;
}
else
{
*buf = XLogReadBufferExtended(rnode, forknum, blkno, mode);
if (BufferIsValid(*buf))
{
if (mode != RBM_ZERO_AND_LOCK && mode != RBM_ZERO_AND_CLEANUP_LOCK)
{
if (get_cleanup_lock)
LockBufferForCleanup(*buf);
else
LockBuffer(*buf, BUFFER_LOCK_EXCLUSIVE);
}
if (lsn <= PageGetLSN(BufferGetPage(*buf)))
return BLK_DONE;
else
return BLK_NEEDS_REDO;
}
else
return BLK_NOTFOUND;
}
}
static void
spgRedoAddNode(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
char *ptr = XLogRecGetData(record);
spgxlogAddNode *xldata = (spgxlogAddNode *) ptr;
char *innerTuple;
SpGistInnerTupleData innerTupleHdr;
SpGistState state;
Buffer buffer;
Page page;
XLogRedoAction action;
ptr += sizeof(spgxlogAddNode);
innerTuple = ptr;
/* the tuple is unaligned, so make a copy to access its header */
memcpy(&innerTupleHdr, innerTuple, sizeof(SpGistInnerTupleData));
fillFakeState(&state, xldata->stateSrc);
if (!XLogRecHasBlockRef(record, 1))
{
/* update in place */
Assert(xldata->parentBlk == -1);
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
page = BufferGetPage(buffer);
PageIndexTupleDelete(page, xldata->offnum);
if (PageAddItem(page, (Item) innerTuple, innerTupleHdr.size,
xldata->offnum,
false, false) != xldata->offnum)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
innerTupleHdr.size);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
else
{
BlockNumber blkno;
BlockNumber blknoNew;
XLogRecGetBlockTag(record, 0, NULL, NULL, &blkno);
XLogRecGetBlockTag(record, 1, NULL, NULL, &blknoNew);
/*
* In normal operation we would have all three pages (source, dest,
* and parent) locked simultaneously; but in WAL replay it should be
* safe to update them one at a time, as long as we do it in the right
* order. We must insert the new tuple before replacing the old tuple
* with the redirect tuple.
*/
/* Install new tuple first so redirect is valid */
if (xldata->newPage)
{
/* AddNode is not used for nulls pages */
buffer = XLogInitBufferForRedo(record, 1);
SpGistInitBuffer(buffer, 0);
action = BLK_NEEDS_REDO;
}
else
action = XLogReadBufferForRedo(record, 1, &buffer);
if (action == BLK_NEEDS_REDO)
{
page = BufferGetPage(buffer);
addOrReplaceTuple(page, (Item) innerTuple,
innerTupleHdr.size, xldata->offnumNew);
/*
* If parent is in this same page, update it now.
*/
if (xldata->parentBlk == 1)
{
SpGistInnerTuple parentTuple;
parentTuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parentTuple, xldata->nodeI,
blknoNew, xldata->offnumNew);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* Delete old tuple, replacing it with redirect or placeholder tuple */
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
SpGistDeadTuple dt;
page = BufferGetPage(buffer);
if (state.isBuild)
dt = spgFormDeadTuple(&state, SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
else
dt = spgFormDeadTuple(&state, SPGIST_REDIRECT,
blknoNew,
xldata->offnumNew);
PageIndexTupleDelete(page, xldata->offnum);
if (PageAddItem(page, (Item) dt, dt->size,
xldata->offnum,
false, false) != xldata->offnum)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
dt->size);
if (state.isBuild)
SpGistPageGetOpaque(page)->nPlaceholder++;
else
SpGistPageGetOpaque(page)->nRedirection++;
/*
* If parent is in this same page, update it now.
*/
if (xldata->parentBlk == 0)
{
SpGistInnerTuple parentTuple;
parentTuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parentTuple, xldata->nodeI,
blknoNew, xldata->offnumNew);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/*
* Update parent downlink (if we didn't do it as part of the source or
* destination page update already).
*/
if (xldata->parentBlk == 2)
{
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
SpGistInnerTuple parentTuple;
page = BufferGetPage(buffer);
parentTuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parentTuple, xldata->nodeI,
blknoNew, xldata->offnumNew);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
}
}
/*
* Decode XLOG_HEAP2_MULTI_INSERT_insert record into multiple tuplebufs.
*
* Currently MULTI_INSERT will always contain the full tuples.
*/
static void
DecodeMultiInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
{
XLogReaderState *r = buf->record;
xl_heap_multi_insert *xlrec;
int i;
char *data;
char *tupledata;
Size tuplelen;
RelFileNode rnode;
xlrec = (xl_heap_multi_insert *) XLogRecGetData(r);
/* only interested in our database */
XLogRecGetBlockTag(r, 0, &rnode, NULL, NULL);
if (rnode.dbNode != ctx->slot->data.database)
return;
/* output plugin doesn't look for this origin, no need to queue */
if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
return;
tupledata = XLogRecGetBlockData(r, 0, &tuplelen);
data = tupledata;
for (i = 0; i < xlrec->ntuples; i++)
{
ReorderBufferChange *change;
xl_multi_insert_tuple *xlhdr;
int datalen;
ReorderBufferTupleBuf *tuple;
change = ReorderBufferGetChange(ctx->reorder);
change->action = REORDER_BUFFER_CHANGE_INSERT;
change->origin_id = XLogRecGetOrigin(r);
memcpy(&change->data.tp.relnode, &rnode, sizeof(RelFileNode));
/*
* CONTAINS_NEW_TUPLE will always be set currently as multi_insert
* isn't used for catalogs, but better be future proof.
*
* We decode the tuple in pretty much the same way as DecodeXLogTuple,
* but since the layout is slightly different, we can't use it here.
*/
if (xlrec->flags & XLH_INSERT_CONTAINS_NEW_TUPLE)
{
change->data.tp.newtuple = ReorderBufferGetTupleBuf(ctx->reorder);
tuple = change->data.tp.newtuple;
/* not a disk based tuple */
ItemPointerSetInvalid(&tuple->tuple.t_self);
xlhdr = (xl_multi_insert_tuple *) SHORTALIGN(data);
data = ((char *) xlhdr) + SizeOfMultiInsertTuple;
datalen = xlhdr->datalen;
/*
* We can only figure this out after reassembling the
* transactions.
*/
tuple->tuple.t_tableOid = InvalidOid;
tuple->tuple.t_data = &tuple->t_data.header;
tuple->tuple.t_len = datalen + SizeofHeapTupleHeader;
memset(&tuple->t_data.header, 0, SizeofHeapTupleHeader);
memcpy((char *) &tuple->t_data.header + SizeofHeapTupleHeader,
(char *) data,
datalen);
data += datalen;
tuple->t_data.header.t_infomask = xlhdr->t_infomask;
tuple->t_data.header.t_infomask2 = xlhdr->t_infomask2;
tuple->t_data.header.t_hoff = xlhdr->t_hoff;
}
/*
* Reset toast reassembly state only after the last row in the last
* xl_multi_insert_tuple record emitted by one heap_multi_insert()
* call.
*/
if (xlrec->flags & XLH_INSERT_LAST_IN_MULTI &&
(i + 1) == xlrec->ntuples)
change->data.tp.clear_toast_afterwards = true;
else
change->data.tp.clear_toast_afterwards = false;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r),
buf->origptr, change);
}
Assert(data == tupledata + tuplelen);
}
/*
* replay addition of overflow page for hash index
*/
static void
hash_xlog_add_ovfl_page(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_hash_add_ovfl_page *xlrec = (xl_hash_add_ovfl_page *) XLogRecGetData(record);
Buffer leftbuf;
Buffer ovflbuf;
Buffer metabuf;
BlockNumber leftblk;
BlockNumber rightblk;
BlockNumber newmapblk = InvalidBlockNumber;
Page ovflpage;
HashPageOpaque ovflopaque;
uint32 *num_bucket;
char *data;
Size datalen PG_USED_FOR_ASSERTS_ONLY;
bool new_bmpage = false;
XLogRecGetBlockTag(record, 0, NULL, NULL, &rightblk);
XLogRecGetBlockTag(record, 1, NULL, NULL, &leftblk);
ovflbuf = XLogInitBufferForRedo(record, 0);
Assert(BufferIsValid(ovflbuf));
data = XLogRecGetBlockData(record, 0, &datalen);
num_bucket = (uint32 *) data;
Assert(datalen == sizeof(uint32));
_hash_initbuf(ovflbuf, InvalidBlockNumber, *num_bucket, LH_OVERFLOW_PAGE,
true);
/* update backlink */
ovflpage = BufferGetPage(ovflbuf);
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
ovflopaque->hasho_prevblkno = leftblk;
PageSetLSN(ovflpage, lsn);
MarkBufferDirty(ovflbuf);
if (XLogReadBufferForRedo(record, 1, &leftbuf) == BLK_NEEDS_REDO)
{
Page leftpage;
HashPageOpaque leftopaque;
leftpage = BufferGetPage(leftbuf);
leftopaque = (HashPageOpaque) PageGetSpecialPointer(leftpage);
leftopaque->hasho_nextblkno = rightblk;
PageSetLSN(leftpage, lsn);
MarkBufferDirty(leftbuf);
}
if (BufferIsValid(leftbuf))
UnlockReleaseBuffer(leftbuf);
UnlockReleaseBuffer(ovflbuf);
/*
* Note: in normal operation, we'd update the bitmap and meta page while
* still holding lock on the overflow pages. But during replay it's not
* necessary to hold those locks, since no other index updates can be
* happening concurrently.
*/
if (XLogRecHasBlockRef(record, 2))
{
Buffer mapbuffer;
if (XLogReadBufferForRedo(record, 2, &mapbuffer) == BLK_NEEDS_REDO)
{
Page mappage = (Page) BufferGetPage(mapbuffer);
uint32 *freep = NULL;
char *data;
uint32 *bitmap_page_bit;
freep = HashPageGetBitmap(mappage);
data = XLogRecGetBlockData(record, 2, &datalen);
bitmap_page_bit = (uint32 *) data;
SETBIT(freep, *bitmap_page_bit);
PageSetLSN(mappage, lsn);
MarkBufferDirty(mapbuffer);
}
if (BufferIsValid(mapbuffer))
UnlockReleaseBuffer(mapbuffer);
}
if (XLogRecHasBlockRef(record, 3))
{
Buffer newmapbuf;
newmapbuf = XLogInitBufferForRedo(record, 3);
_hash_initbitmapbuffer(newmapbuf, xlrec->bmsize, true);
new_bmpage = true;
newmapblk = BufferGetBlockNumber(newmapbuf);
MarkBufferDirty(newmapbuf);
PageSetLSN(BufferGetPage(newmapbuf), lsn);
UnlockReleaseBuffer(newmapbuf);
}
if (XLogReadBufferForRedo(record, 4, &metabuf) == BLK_NEEDS_REDO)
{
HashMetaPage metap;
Page page;
uint32 *firstfree_ovflpage;
data = XLogRecGetBlockData(record, 4, &datalen);
firstfree_ovflpage = (uint32 *) data;
page = BufferGetPage(metabuf);
metap = HashPageGetMeta(page);
metap->hashm_firstfree = *firstfree_ovflpage;
if (!xlrec->bmpage_found)
{
metap->hashm_spares[metap->hashm_ovflpoint]++;
if (new_bmpage)
{
Assert(BlockNumberIsValid(newmapblk));
metap->hashm_mapp[metap->hashm_nmaps] = newmapblk;
metap->hashm_nmaps++;
metap->hashm_spares[metap->hashm_ovflpoint]++;
}
}
PageSetLSN(page, lsn);
MarkBufferDirty(metabuf);
}
if (BufferIsValid(metabuf))
UnlockReleaseBuffer(metabuf);
}
/*
* replay delete operation in hash index to remove
* tuples marked as DEAD during index tuple insertion.
*/
static void
hash_xlog_vacuum_one_page(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_hash_vacuum_one_page *xldata;
Buffer buffer;
Buffer metabuf;
Page page;
XLogRedoAction action;
HashPageOpaque pageopaque;
xldata = (xl_hash_vacuum_one_page *) XLogRecGetData(record);
/*
* If we have any conflict processing to do, it must happen before we
* update the page.
*
* Hash index records that are marked as LP_DEAD and being removed during
* hash index tuple insertion can conflict with standby queries. You might
* think that vacuum records would conflict as well, but we've handled
* that already. XLOG_HEAP2_CLEANUP_INFO records provide the highest xid
* cleaned by the vacuum of the heap and so we can resolve any conflicts
* just once when that arrives. After that we know that no conflicts
* exist from individual hash index vacuum records on that index.
*/
if (InHotStandby)
{
TransactionId latestRemovedXid =
hash_xlog_vacuum_get_latestRemovedXid(record);
RelFileNode rnode;
XLogRecGetBlockTag(record, 0, &rnode, NULL, NULL);
ResolveRecoveryConflictWithSnapshot(latestRemovedXid, rnode);
}
action = XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, true, &buffer);
if (action == BLK_NEEDS_REDO)
{
char *ptr;
Size len;
ptr = XLogRecGetBlockData(record, 0, &len);
page = (Page) BufferGetPage(buffer);
if (len > 0)
{
OffsetNumber *unused;
OffsetNumber *unend;
unused = (OffsetNumber *) ptr;
unend = (OffsetNumber *) ((char *) ptr + len);
if ((unend - unused) > 0)
PageIndexMultiDelete(page, unused, unend - unused);
}
/*
* Mark the page as not containing any LP_DEAD items. See comments
* in _hash_vacuum_one_page() for details.
*/
pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
pageopaque->hasho_flag &= ~LH_PAGE_HAS_DEAD_TUPLES;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
if (XLogReadBufferForRedo(record, 1, &metabuf) == BLK_NEEDS_REDO)
{
Page metapage;
HashMetaPage metap;
metapage = BufferGetPage(metabuf);
metap = HashPageGetMeta(metapage);
metap->hashm_ntuples -= xldata->ntuples;
PageSetLSN(metapage, lsn);
MarkBufferDirty(metabuf);
}
if (BufferIsValid(metabuf))
UnlockReleaseBuffer(metabuf);
}
static void
spgRedoAddLeaf(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
char *ptr = XLogRecGetData(record);
spgxlogAddLeaf *xldata = (spgxlogAddLeaf *) ptr;
char *leafTuple;
SpGistLeafTupleData leafTupleHdr;
Buffer buffer;
Page page;
XLogRedoAction action;
ptr += sizeof(spgxlogAddLeaf);
leafTuple = ptr;
/* the leaf tuple is unaligned, so make a copy to access its header */
memcpy(&leafTupleHdr, leafTuple, sizeof(SpGistLeafTupleData));
/*
* In normal operation we would have both current and parent pages locked
* simultaneously; but in WAL replay it should be safe to update the leaf
* page before updating the parent.
*/
if (xldata->newPage)
{
buffer = XLogInitBufferForRedo(record, 0);
SpGistInitBuffer(buffer,
SPGIST_LEAF | (xldata->storesNulls ? SPGIST_NULLS : 0));
action = BLK_NEEDS_REDO;
}
else
action = XLogReadBufferForRedo(record, 0, &buffer);
if (action == BLK_NEEDS_REDO)
{
page = BufferGetPage(buffer);
/* insert new tuple */
if (xldata->offnumLeaf != xldata->offnumHeadLeaf)
{
/* normal cases, tuple was added by SpGistPageAddNewItem */
addOrReplaceTuple(page, (Item) leafTuple, leafTupleHdr.size,
xldata->offnumLeaf);
/* update head tuple's chain link if needed */
if (xldata->offnumHeadLeaf != InvalidOffsetNumber)
{
SpGistLeafTuple head;
head = (SpGistLeafTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumHeadLeaf));
Assert(head->nextOffset == leafTupleHdr.nextOffset);
head->nextOffset = xldata->offnumLeaf;
}
}
else
{
/* replacing a DEAD tuple */
PageIndexTupleDelete(page, xldata->offnumLeaf);
if (PageAddItem(page,
(Item) leafTuple, leafTupleHdr.size,
xldata->offnumLeaf, false, false) != xldata->offnumLeaf)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
leafTupleHdr.size);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
/* update parent downlink if necessary */
if (xldata->offnumParent != InvalidOffsetNumber)
{
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
SpGistInnerTuple tuple;
BlockNumber blknoLeaf;
XLogRecGetBlockTag(record, 0, NULL, NULL, &blknoLeaf);
page = BufferGetPage(buffer);
tuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(tuple, xldata->nodeI,
blknoLeaf, xldata->offnumLeaf);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
}
static void
spgRedoPickSplit(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
char *ptr = XLogRecGetData(record);
spgxlogPickSplit *xldata = (spgxlogPickSplit *) ptr;
char *innerTuple;
SpGistInnerTupleData innerTupleHdr;
SpGistState state;
OffsetNumber *toDelete;
OffsetNumber *toInsert;
uint8 *leafPageSelect;
Buffer srcBuffer;
Buffer destBuffer;
Buffer innerBuffer;
Page srcPage;
Page destPage;
Page page;
int i;
BlockNumber blknoInner;
XLogRedoAction action;
XLogRecGetBlockTag(record, 2, NULL, NULL, &blknoInner);
fillFakeState(&state, xldata->stateSrc);
ptr += SizeOfSpgxlogPickSplit;
toDelete = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nDelete;
toInsert = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nInsert;
leafPageSelect = (uint8 *) ptr;
ptr += sizeof(uint8) * xldata->nInsert;
innerTuple = ptr;
/* the inner tuple is unaligned, so make a copy to access its header */
memcpy(&innerTupleHdr, innerTuple, sizeof(SpGistInnerTupleData));
ptr += innerTupleHdr.size;
/* now ptr points to the list of leaf tuples */
if (xldata->isRootSplit)
{
/* when splitting root, we touch it only in the guise of new inner */
srcBuffer = InvalidBuffer;
srcPage = NULL;
}
else if (xldata->initSrc)
{
/* just re-init the source page */
srcBuffer = XLogInitBufferForRedo(record, 0);
srcPage = (Page) BufferGetPage(srcBuffer);
SpGistInitBuffer(srcBuffer,
SPGIST_LEAF | (xldata->storesNulls ? SPGIST_NULLS : 0));
/* don't update LSN etc till we're done with it */
}
else
{
/*
* Delete the specified tuples from source page. (In case we're in
* Hot Standby, we need to hold lock on the page till we're done
* inserting leaf tuples and the new inner tuple, else the added
* redirect tuple will be a dangling link.)
*/
srcPage = NULL;
if (XLogReadBufferForRedo(record, 0, &srcBuffer) == BLK_NEEDS_REDO)
{
srcPage = BufferGetPage(srcBuffer);
/*
* We have it a bit easier here than in doPickSplit(), because we
* know the inner tuple's location already, so we can inject the
* correct redirection tuple now.
*/
if (!state.isBuild)
spgPageIndexMultiDelete(&state, srcPage,
toDelete, xldata->nDelete,
SPGIST_REDIRECT,
SPGIST_PLACEHOLDER,
blknoInner,
xldata->offnumInner);
else
spgPageIndexMultiDelete(&state, srcPage,
toDelete, xldata->nDelete,
SPGIST_PLACEHOLDER,
SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
/* don't update LSN etc till we're done with it */
}
}
/* try to access dest page if any */
if (!XLogRecHasBlockRef(record, 1))
{
destBuffer = InvalidBuffer;
destPage = NULL;
}
else if (xldata->initDest)
{
/* just re-init the dest page */
destBuffer = XLogInitBufferForRedo(record, 1);
destPage = (Page) BufferGetPage(destBuffer);
SpGistInitBuffer(destBuffer,
SPGIST_LEAF | (xldata->storesNulls ? SPGIST_NULLS : 0));
/* don't update LSN etc till we're done with it */
}
else
{
/*
* We could probably release the page lock immediately in the
* full-page-image case, but for safety let's hold it till later.
*/
if (XLogReadBufferForRedo(record, 1, &destBuffer) == BLK_NEEDS_REDO)
destPage = (Page) BufferGetPage(destBuffer);
else
destPage = NULL; /* don't do any page updates */
}
/* restore leaf tuples to src and/or dest page */
for (i = 0; i < xldata->nInsert; i++)
{
char *leafTuple;
SpGistLeafTupleData leafTupleHdr;
/* the tuples are not aligned, so must copy to access the size field. */
leafTuple = ptr;
memcpy(&leafTupleHdr, leafTuple, sizeof(SpGistLeafTupleData));
ptr += leafTupleHdr.size;
page = leafPageSelect[i] ? destPage : srcPage;
if (page == NULL)
continue; /* no need to touch this page */
addOrReplaceTuple(page, (Item) leafTuple, leafTupleHdr.size,
toInsert[i]);
}
/* Now update src and dest page LSNs if needed */
if (srcPage != NULL)
{
PageSetLSN(srcPage, lsn);
MarkBufferDirty(srcBuffer);
}
if (destPage != NULL)
{
PageSetLSN(destPage, lsn);
MarkBufferDirty(destBuffer);
}
/* restore new inner tuple */
if (xldata->initInner)
{
innerBuffer = XLogInitBufferForRedo(record, 2);
SpGistInitBuffer(innerBuffer, (xldata->storesNulls ? SPGIST_NULLS : 0));
action = BLK_NEEDS_REDO;
}
else
action = XLogReadBufferForRedo(record, 2, &innerBuffer);
if (action == BLK_NEEDS_REDO)
{
page = BufferGetPage(innerBuffer);
addOrReplaceTuple(page, (Item) innerTuple, innerTupleHdr.size,
xldata->offnumInner);
/* if inner is also parent, update link while we're here */
if (xldata->innerIsParent)
{
SpGistInnerTuple parent;
parent = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parent, xldata->nodeI,
blknoInner, xldata->offnumInner);
}
PageSetLSN(page, lsn);
MarkBufferDirty(innerBuffer);
}
if (BufferIsValid(innerBuffer))
UnlockReleaseBuffer(innerBuffer);
/*
* Now we can release the leaf-page locks. It's okay to do this before
* updating the parent downlink.
*/
if (BufferIsValid(srcBuffer))
UnlockReleaseBuffer(srcBuffer);
if (BufferIsValid(destBuffer))
UnlockReleaseBuffer(destBuffer);
/* update parent downlink, unless we did it above */
if (XLogRecHasBlockRef(record, 3))
{
Buffer parentBuffer;
if (XLogReadBufferForRedo(record, 3, &parentBuffer) == BLK_NEEDS_REDO)
{
SpGistInnerTuple parent;
page = BufferGetPage(parentBuffer);
parent = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parent, xldata->nodeI,
blknoInner, xldata->offnumInner);
PageSetLSN(page, lsn);
MarkBufferDirty(parentBuffer);
}
if (BufferIsValid(parentBuffer))
UnlockReleaseBuffer(parentBuffer);
}
else
Assert(xldata->innerIsParent || xldata->isRootSplit);
}
static void
spgRedoVacuumRedirect(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
char *ptr = XLogRecGetData(record);
spgxlogVacuumRedirect *xldata = (spgxlogVacuumRedirect *) ptr;
OffsetNumber *itemToPlaceholder;
Buffer buffer;
itemToPlaceholder = xldata->offsets;
/*
* If any redirection tuples are being removed, make sure there are no
* live Hot Standby transactions that might need to see them.
*/
if (InHotStandby)
{
if (TransactionIdIsValid(xldata->newestRedirectXid))
{
RelFileNode node;
XLogRecGetBlockTag(record, 0, &node, NULL, NULL);
ResolveRecoveryConflictWithSnapshot(xldata->newestRedirectXid,
node);
}
}
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
SpGistPageOpaque opaque = SpGistPageGetOpaque(page);
int i;
/* Convert redirect pointers to plain placeholders */
for (i = 0; i < xldata->nToPlaceholder; i++)
{
SpGistDeadTuple dt;
dt = (SpGistDeadTuple) PageGetItem(page,
PageGetItemId(page, itemToPlaceholder[i]));
Assert(dt->tupstate == SPGIST_REDIRECT);
dt->tupstate = SPGIST_PLACEHOLDER;
ItemPointerSetInvalid(&dt->pointer);
}
Assert(opaque->nRedirection >= xldata->nToPlaceholder);
opaque->nRedirection -= xldata->nToPlaceholder;
opaque->nPlaceholder += xldata->nToPlaceholder;
/* Remove placeholder tuples at end of page */
if (xldata->firstPlaceholder != InvalidOffsetNumber)
{
int max = PageGetMaxOffsetNumber(page);
OffsetNumber *toDelete;
toDelete = palloc(sizeof(OffsetNumber) * max);
for (i = xldata->firstPlaceholder; i <= max; i++)
toDelete[i - xldata->firstPlaceholder] = i;
i = max - xldata->firstPlaceholder + 1;
Assert(opaque->nPlaceholder >= i);
opaque->nPlaceholder -= i;
/* The array is sorted, so can use PageIndexMultiDelete */
PageIndexMultiDelete(page, toDelete, i);
pfree(toDelete);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}