/*
* XLogReadBufferForRedoExtended
* Like XLogReadBufferForRedo, but with extra options.
*
* If mode is RBM_ZERO or RBM_ZERO_ON_ERROR, if the page doesn't exist, the
* relation is extended with all-zeroes pages up to the referenced block
* number. In RBM_ZERO mode, the return value is always BLK_NEEDS_REDO.
*
* If 'get_cleanup_lock' is true, a "cleanup lock" is acquired on the buffer
* using LockBufferForCleanup(), instead of a regular exclusive lock.
*/
XLogRedoAction
XLogReadBufferForRedoExtended(XLogRecPtr lsn, XLogRecord *record,
int block_index, RelFileNode rnode,
ForkNumber forkno, BlockNumber blkno,
ReadBufferMode mode, bool get_cleanup_lock,
Buffer *buf)
{
if (record->xl_info & XLR_BKP_BLOCK(block_index))
{
*buf = RestoreBackupBlock(lsn, record, block_index,
get_cleanup_lock, true);
return BLK_RESTORED;
}
else
{
*buf = XLogReadBufferExtended(rnode, forkno, blkno, mode);
if (BufferIsValid(*buf))
{
LockBuffer(*buf, BUFFER_LOCK_EXCLUSIVE);
if (lsn <= PageGetLSN(BufferGetPage(*buf)))
return BLK_DONE;
else
return BLK_NEEDS_REDO;
}
else
return BLK_NOTFOUND;
}
}
/*
* XLogRecordPageWithFreeSpace - like RecordPageWithFreeSpace, for use in
* WAL replay
*/
void
XLogRecordPageWithFreeSpace(RelFileNode rnode, BlockNumber heapBlk,
Size spaceAvail)
{
int new_cat = fsm_space_avail_to_cat(spaceAvail);
FSMAddress addr;
uint16 slot;
BlockNumber blkno;
Buffer buf;
Page page;
/* Get the location of the FSM byte representing the heap block */
addr = fsm_get_location(heapBlk, &slot);
blkno = fsm_logical_to_physical(addr);
/* If the page doesn't exist already, extend */
buf = XLogReadBufferExtended(rnode, FSM_FORKNUM, blkno, RBM_ZERO_ON_ERROR);
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
page = BufferGetPage(buf);
if (PageIsNew(page))
PageInit(page, BLCKSZ, 0);
if (fsm_set_avail(page, slot, new_cat))
MarkBufferDirtyHint(buf, false);
UnlockReleaseBuffer(buf);
}
/*
* XLogReadBuffer
* Read a page during XLOG replay.
*
* This is a shorthand of XLogReadBufferExtended() followed by
* LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE), for reading from the main
* fork.
*
* (Getting the buffer lock is not really necessary during single-process
* crash recovery, but some subroutines such as MarkBufferDirty will complain
* if we don't have the lock. In hot standby mode it's definitely necessary.)
*
* The returned buffer is exclusively-locked.
*
* For historical reasons, instead of a ReadBufferMode argument, this only
* supports RBM_ZERO (init == true) and RBM_NORMAL (init == false) modes.
*/
Buffer
XLogReadBuffer(RelFileNode rnode, BlockNumber blkno, bool init)
{
Buffer buf;
buf = XLogReadBufferExtended(rnode, MAIN_FORKNUM, blkno,
init ? RBM_ZERO : RBM_NORMAL);
if (BufferIsValid(buf))
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
return buf;
}
/*
* XLogRecordPageWithFreeSpace - like RecordPageWithFreeSpace, for use in
* WAL replay
*/
void
XLogRecordPageWithFreeSpace(RelFileNode rnode, BlockNumber heapBlk,
Size spaceAvail)
{
int new_cat = fsm_space_avail_to_cat(spaceAvail);
FSMAddress addr;
uint16 slot;
BlockNumber blkno;
Buffer buf;
Page page;
bool write_to_fsm;
/* This is meant to mirror the logic in fsm_allow_writes() */
if (heapBlk >= HEAP_FSM_CREATION_THRESHOLD)
write_to_fsm = true;
else
{
/* Open the relation at smgr level */
SMgrRelation smgr = smgropen(rnode, InvalidBackendId);
if (smgrexists(smgr, FSM_FORKNUM))
write_to_fsm = true;
else
{
BlockNumber heap_nblocks = smgrnblocks(smgr, MAIN_FORKNUM);
if (heap_nblocks > HEAP_FSM_CREATION_THRESHOLD)
write_to_fsm = true;
else
write_to_fsm = false;
}
}
if (!write_to_fsm)
return;
/* Get the location of the FSM byte representing the heap block */
addr = fsm_get_location(heapBlk, &slot);
blkno = fsm_logical_to_physical(addr);
/* If the page doesn't exist already, extend */
buf = XLogReadBufferExtended(rnode, FSM_FORKNUM, blkno, RBM_ZERO_ON_ERROR);
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
page = BufferGetPage(buf);
if (PageIsNew(page))
PageInit(page, BLCKSZ, 0);
if (fsm_set_avail(page, slot, new_cat))
MarkBufferDirtyHint(buf, false);
UnlockReleaseBuffer(buf);
}
/*
* 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);
}
/*
* 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;
}
}
