/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the heap page. The LSN of the visibility map page is
* advanced to that, to make sure that the visibility map doesn't get flushed
* to disk before the update to the heap page that made all tuples visible.
*
* This is an opportunistic function. It does nothing, unless *buf
* contains the bit for heapBlk. Call visibilitymap_pin first to pin
* the right map page. This function doesn't do any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, XLogRecPtr recptr,
Buffer *buf)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
/* Check that we have the right page pinned */
if (!BufferIsValid(*buf) || BufferGetBlockNumber(*buf) != mapBlock)
return;
page = BufferGetPage(*buf);
map = PageGetContents(page);
LockBuffer(*buf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
map[mapByte] |= (1 << mapBit);
if (XLByteLT(PageGetLSN(page), recptr))
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(*buf);
}
LockBuffer(*buf, BUFFER_LOCK_UNLOCK);
}
/*
* visibilitymap_clear - clear a bit in visibility map
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_clear(Relation rel, BlockNumber heapBlk, Buffer buf)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
int mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
int mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
uint8 mask = 1 << mapBit;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk);
#endif
if (!BufferIsValid(buf) || BufferGetBlockNumber(buf) != mapBlock)
elog(ERROR, "wrong buffer passed to visibilitymap_clear");
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
map = PageGetContents(BufferGetPage(buf));
if (map[mapByte] & mask)
{
map[mapByte] &= ~mask;
MarkBufferDirty(buf);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
/*
* visibilitymap_clear - clear a bit in visibility map
*
* Clear a bit in the visibility map, marking that not all tuples are
* visible to all transactions anymore.
*/
void
visibilitymap_clear(Relation rel, BlockNumber heapBlk)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
int mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
int mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
uint8 mask = 1 << mapBit;
Buffer mapBuffer;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk);
#endif
mapBuffer = vm_readbuf(rel, mapBlock, false);
if (!BufferIsValid(mapBuffer))
return; /* nothing to do */
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
map = PageGetContents(BufferGetPage(mapBuffer));
if (map[mapByte] & mask)
{
map[mapByte] &= ~mask;
MarkBufferDirty(mapBuffer);
}
UnlockReleaseBuffer(mapBuffer);
}
/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
* or InvalidXLogRecPtr in normal running. The page LSN is advanced to the
* one provided; in normal running, we generate a new XLOG record and set the
* page LSN to that value. cutoff_xid is the largest xmin on the page being
* marked all-visible; it is needed for Hot Standby, and can be
* InvalidTransactionId if the page contains no tuples.
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, XLogRecPtr recptr,
Buffer buf, TransactionId cutoff_xid)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
/* Check that we have the right page pinned */
if (!BufferIsValid(buf) || BufferGetBlockNumber(buf) != mapBlock)
elog(ERROR, "wrong buffer passed to visibilitymap_set");
page = BufferGetPage(buf);
map = PageGetContents(page);
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
START_CRIT_SECTION();
map[mapByte] |= (1 << mapBit);
MarkBufferDirty(buf);
if (RelationNeedsWAL(rel))
{
if (XLogRecPtrIsInvalid(recptr))
recptr = log_heap_visible(rel->rd_node, heapBlk, buf,
cutoff_xid);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
END_CRIT_SECTION();
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
/*
* visibilitymap_test - test if a bit is set
*
* Are all tuples on heapBlk visible to all, according to the visibility map?
*
* On entry, *buf should be InvalidBuffer or a valid buffer returned by an
* earlier call to visibilitymap_pin or visibilitymap_test on the same
* relation. On return, *buf is a valid buffer with the map page containing
* the bit for heapBlk, or InvalidBuffer. The caller is responsible for
* releasing *buf after it's done testing and setting bits.
*
* NOTE: This function is typically called without a lock on the heap page,
* so somebody else could change the bit just after we look at it. In fact,
* since we don't lock the visibility map page either, it's even possible that
* someone else could have changed the bit just before we look at it, but yet
* we might see the old value. It is the caller's responsibility to deal with
* all concurrency issues!
*/
bool
visibilitymap_test(Relation rel, BlockNumber heapBlk, Buffer *buf)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
bool result;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_test %s %d", RelationGetRelationName(rel), heapBlk);
#endif
/* Reuse the old pinned buffer if possible */
if (BufferIsValid(*buf))
{
if (BufferGetBlockNumber(*buf) != mapBlock)
{
ReleaseBuffer(*buf);
*buf = InvalidBuffer;
}
}
if (!BufferIsValid(*buf))
{
*buf = vm_readbuf(rel, mapBlock, false);
if (!BufferIsValid(*buf))
return false;
}
map = PageGetContents(BufferGetPage(*buf));
/*
* A single-bit read is atomic. There could be memory-ordering effects
* here, but for performance reasons we make it the caller's job to worry
* about that.
*/
result = (map[mapByte] & (1 << mapBit)) ? true : false;
return result;
}
/*
* visibilitymap_test - test if a bit is set
*
* Are all tuples on heapBlk visible to all, according to the visibility map?
*
* On entry, *buf should be InvalidBuffer or a valid buffer returned by an
* earlier call to visibilitymap_pin or visibilitymap_test on the same
* relation. On return, *buf is a valid buffer with the map page containing
* the bit for heapBlk, or InvalidBuffer. The caller is responsible for
* releasing *buf after it's done testing and setting bits.
*/
bool
visibilitymap_test(Relation rel, BlockNumber heapBlk, Buffer *buf)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
bool result;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_test %s %d", RelationGetRelationName(rel), heapBlk);
#endif
/* Reuse the old pinned buffer if possible */
if (BufferIsValid(*buf))
{
if (BufferGetBlockNumber(*buf) != mapBlock)
{
ReleaseBuffer(*buf);
*buf = InvalidBuffer;
}
}
if (!BufferIsValid(*buf))
{
*buf = vm_readbuf(rel, mapBlock, false);
if (!BufferIsValid(*buf))
return false;
}
map = PageGetContents(BufferGetPage(*buf));
/*
* We don't need to lock the page, as we're only looking at a single bit.
*/
result = (map[mapByte] & (1 << mapBit)) ? true : false;
return result;
}
/*
* visibilitymap_truncate - truncate the visibility map
*
* The caller must hold AccessExclusiveLock on the relation, to ensure that
* other backends receive the smgr invalidation event that this function sends
* before they access the VM again.
*
* nheapblocks is the new size of the heap.
*/
void
visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
{
BlockNumber newnblocks;
/* last remaining block, byte, and bit */
BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks);
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
RelationOpenSmgr(rel);
/*
* If no visibility map has been created yet for this relation, there's
* nothing to truncate.
*/
if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
return;
/*
* Unless the new size is exactly at a visibility map page boundary, the
* tail bits in the last remaining map page, representing truncated heap
* blocks, need to be cleared. This is not only tidy, but also necessary
* because we don't get a chance to clear the bits if the heap is extended
* again.
*/
if (truncByte != 0 || truncBit != 0)
{
Buffer mapBuffer;
Page page;
char *map;
newnblocks = truncBlock + 1;
mapBuffer = vm_readbuf(rel, truncBlock, false);
if (!BufferIsValid(mapBuffer))
{
/* nothing to do, the file was already smaller */
return;
}
page = BufferGetPage(mapBuffer);
map = PageGetContents(page);
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
/* Clear out the unwanted bytes. */
MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
/*
* Mask out the unwanted bits of the last remaining byte.
*
* ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) -
* 1) = 00111111 ((1 << 7) - 1) = 01111111
*/
map[truncByte] &= (1 << truncBit) - 1;
MarkBufferDirty(mapBuffer);
UnlockReleaseBuffer(mapBuffer);
}
else
newnblocks = truncBlock;
if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) <= newnblocks)
{
/* nothing to do, the file was already smaller than requested size */
return;
}
/* Truncate the unused VM pages, and send smgr inval message */
smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks);
/*
* We might as well update the local smgr_vm_nblocks setting. smgrtruncate
* sent an smgr cache inval message, which will cause other backends to
* invalidate their copy of smgr_vm_nblocks, and this one too at the next
* command boundary. But this ensures it isn't outright wrong until then.
*/
if (rel->rd_smgr)
rel->rd_smgr->smgr_vm_nblocks = newnblocks;
}
/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
* or InvalidXLogRecPtr in normal running. The page LSN is advanced to the
* one provided; in normal running, we generate a new___ XLOG record and set the
* page LSN to that value. cutoff_xid is the largest xmin on the page being
* marked all-visible; it is needed for Hot Standby, and can be
* InvalidTransactionId if the page contains no tuples.
*
* Caller is expected to set the heap page's PD_ALL_VISIBLE bit before calling
* this function. Except in recovery, caller should also pass the heap
* buffer. When checksums are enabled and we're not in recovery, we must add
* the heap buffer to the WAL chain to protect it from being torn.
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, Buffer heapBuf,
XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
Assert(InRecovery || BufferIsValid(heapBuf));
/* Check that we have the right heap page pinned, if present */
if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
/* Check that we have the right VM page pinned */
if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
page = BufferGetPage(vmBuf);
map = PageGetContents(page);
LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
START_CRIT_SECTION();
map[mapByte] |= (1 << mapBit);
MarkBufferDirty(vmBuf);
if (RelationNeedsWAL(rel))
{
if (XLogRecPtrIsInvalid(recptr))
{
Assert(!InRecovery);
recptr = log_heap_visible(rel->rd_node, heapBuf, vmBuf,
cutoff_xid);
/*
* If data checksums are enabled (or wal_log_hints=on), we
* need to protect the heap page from being torn.
*/
if (XLogHintBitIsNeeded())
{
Page heapPage = BufferGetPage(heapBuf);
/* caller is expected to set PD_ALL_VISIBLE first */
Assert(PageIsAllVisible(heapPage));
PageSetLSN(heapPage, recptr);
}
}
PageSetLSN(page, recptr);
}
END_CRIT_SECTION();
}
LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
}
/*
* visibilitymap_test - truncate the visibility map
*/
void
visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
{
BlockNumber newnblocks;
/* last remaining block, byte, and bit */
BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks);
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
/*
* If no visibility map has been created yet for this relation, there's
* nothing to truncate.
*/
if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
return;
/*
* Unless the new size is exactly at a visibility map page boundary, the
* tail bits in the last remaining map page, representing truncated heap
* blocks, need to be cleared. This is not only tidy, but also necessary
* because we don't get a chance to clear the bits if the heap is extended
* again.
*/
if (truncByte != 0 || truncBit != 0)
{
Buffer mapBuffer;
Page page;
char *map;
newnblocks = truncBlock + 1;
mapBuffer = vm_readbuf(rel, truncBlock, false);
if (!BufferIsValid(mapBuffer))
{
/* nothing to do, the file was already smaller */
return;
}
page = BufferGetPage(mapBuffer);
map = PageGetContents(page);
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
/* Clear out the unwanted bytes. */
MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
/*
* Mask out the unwanted bits of the last remaining byte.
*
* ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) -
* 1) = 00111111 ((1 << 7) - 1) = 01111111
*/
map[truncByte] &= (1 << truncBit) - 1;
MarkBufferDirty(mapBuffer);
UnlockReleaseBuffer(mapBuffer);
}
else
newnblocks = truncBlock;
if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) < newnblocks)
{
/* nothing to do, the file was already smaller than requested size */
return;
}
smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks,
rel->rd_istemp);
/*
* Need to invalidate the relcache entry, because rd_vm_nblocks seen by
* other backends is no longer valid.
*/
if (!InRecovery)
CacheInvalidateRelcache(rel);
rel->rd_vm_nblocks = newnblocks;
}
