Header And Logo
|
#include "postgres.h"#include "access/heapam.h"#include "access/hio.h"#include "access/htup_details.h"#include "access/visibilitymap.h"#include "storage/bufmgr.h"#include "storage/freespace.h"#include "storage/lmgr.h"#include "storage/smgr.h"
Go to the source code of this file.
Functions | |
| void | RelationPutHeapTuple (Relation relation, Buffer buffer, HeapTuple tuple) |
| static Buffer | ReadBufferBI (Relation relation, BlockNumber targetBlock, BulkInsertState bistate) |
| static void | GetVisibilityMapPins (Relation relation, Buffer buffer1, Buffer buffer2, BlockNumber block1, BlockNumber block2, Buffer *vmbuffer1, Buffer *vmbuffer2) |
| Buffer | RelationGetBufferForTuple (Relation relation, Size len, Buffer otherBuffer, int options, BulkInsertState bistate, Buffer *vmbuffer, Buffer *vmbuffer_other) |
| static void GetVisibilityMapPins | ( | Relation | relation, | |
| Buffer | buffer1, | |||
| Buffer | buffer2, | |||
| BlockNumber | block1, | |||
| BlockNumber | block2, | |||
| Buffer * | vmbuffer1, | |||
| Buffer * | vmbuffer2 | |||
| ) | [static] |
Definition at line 109 of file hio.c.
References Assert, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetPage, BufferIsValid, InvalidBuffer, LockBuffer(), PageIsAllVisible, visibilitymap_pin(), and visibilitymap_pin_ok().
Referenced by RelationGetBufferForTuple().
{
bool need_to_pin_buffer1;
bool need_to_pin_buffer2;
Assert(BufferIsValid(buffer1));
Assert(buffer2 == InvalidBuffer || buffer1 <= buffer2);
while (1)
{
/* Figure out which pins we need but don't have. */
need_to_pin_buffer1 = PageIsAllVisible(BufferGetPage(buffer1))
&& !visibilitymap_pin_ok(block1, *vmbuffer1);
need_to_pin_buffer2 = buffer2 != InvalidBuffer
&& PageIsAllVisible(BufferGetPage(buffer2))
&& !visibilitymap_pin_ok(block2, *vmbuffer2);
if (!need_to_pin_buffer1 && !need_to_pin_buffer2)
return;
/* We must unlock both buffers before doing any I/O. */
LockBuffer(buffer1, BUFFER_LOCK_UNLOCK);
if (buffer2 != InvalidBuffer && buffer2 != buffer1)
LockBuffer(buffer2, BUFFER_LOCK_UNLOCK);
/* Get pins. */
if (need_to_pin_buffer1)
visibilitymap_pin(relation, block1, vmbuffer1);
if (need_to_pin_buffer2)
visibilitymap_pin(relation, block2, vmbuffer2);
/* Relock buffers. */
LockBuffer(buffer1, BUFFER_LOCK_EXCLUSIVE);
if (buffer2 != InvalidBuffer && buffer2 != buffer1)
LockBuffer(buffer2, BUFFER_LOCK_EXCLUSIVE);
/*
* If there are two buffers involved and we pinned just one of them,
* it's possible that the second one became all-visible while we were
* busy pinning the first one. If it looks like that's a possible
* scenario, we'll need to make a second pass through this loop.
*/
if (buffer2 == InvalidBuffer || buffer1 == buffer2
|| (need_to_pin_buffer1 && need_to_pin_buffer2))
break;
}
}
| static Buffer ReadBufferBI | ( | Relation | relation, | |
| BlockNumber | targetBlock, | |||
| BulkInsertState | bistate | |||
| ) | [static] |
Definition at line 67 of file hio.c.
References BufferGetBlockNumber(), BulkInsertStateData::current_buf, IncrBufferRefCount(), InvalidBuffer, MAIN_FORKNUM, RBM_NORMAL, ReadBuffer(), ReadBufferExtended(), ReleaseBuffer(), and BulkInsertStateData::strategy.
Referenced by RelationGetBufferForTuple().
{
Buffer buffer;
/* If not bulk-insert, exactly like ReadBuffer */
if (!bistate)
return ReadBuffer(relation, targetBlock);
/* If we have the desired block already pinned, re-pin and return it */
if (bistate->current_buf != InvalidBuffer)
{
if (BufferGetBlockNumber(bistate->current_buf) == targetBlock)
{
IncrBufferRefCount(bistate->current_buf);
return bistate->current_buf;
}
/* ... else drop the old buffer */
ReleaseBuffer(bistate->current_buf);
bistate->current_buf = InvalidBuffer;
}
/* Perform a read using the buffer strategy */
buffer = ReadBufferExtended(relation, MAIN_FORKNUM, targetBlock,
RBM_NORMAL, bistate->strategy);
/* Save the selected block as target for future inserts */
IncrBufferRefCount(buffer);
bistate->current_buf = buffer;
return buffer;
}
| Buffer RelationGetBufferForTuple | ( | Relation | relation, | |
| Size | len, | |||
| Buffer | otherBuffer, | |||
| int | options, | |||
| BulkInsertState | bistate, | |||
| Buffer * | vmbuffer, | |||
| Buffer * | vmbuffer_other | |||
| ) |
Definition at line 215 of file hio.c.
References Assert, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage, BufferGetPageSize, BulkInsertStateData::current_buf, elog, ereport, errcode(), errmsg(), ERROR, ExclusiveLock, GetPageWithFreeSpace(), GetVisibilityMapPins(), HEAP_DEFAULT_FILLFACTOR, InvalidBlockNumber, InvalidBuffer, LockBuffer(), LockRelationForExtension(), MAXALIGN, MaxHeapTupleSize, P_NEW, PageGetHeapFreeSpace(), PageInit(), PageIsAllVisible, PageIsNew, PANIC, ReadBuffer(), ReadBufferBI(), RecordAndGetPageWithFreeSpace(), RELATION_IS_LOCAL, RelationGetNumberOfBlocks, RelationGetRelationName, RelationGetTargetBlock, RelationGetTargetPageFreeSpace, RelationSetTargetBlock, ReleaseBuffer(), UnlockRelationForExtension(), and visibilitymap_pin().
Referenced by heap_insert(), heap_multi_insert(), and heap_update().
{
bool use_fsm = !(options & HEAP_INSERT_SKIP_FSM);
Buffer buffer = InvalidBuffer;
Page page;
Size pageFreeSpace,
saveFreeSpace;
BlockNumber targetBlock,
otherBlock;
bool needLock;
len = MAXALIGN(len); /* be conservative */
/* Bulk insert is not supported for updates, only inserts. */
Assert(otherBuffer == InvalidBuffer || !bistate);
/*
* If we're gonna fail for oversize tuple, do it right away
*/
if (len > MaxHeapTupleSize)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("row is too big: size %lu, maximum size %lu",
(unsigned long) len,
(unsigned long) MaxHeapTupleSize)));
/* Compute desired extra freespace due to fillfactor option */
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
if (otherBuffer != InvalidBuffer)
otherBlock = BufferGetBlockNumber(otherBuffer);
else
otherBlock = InvalidBlockNumber; /* just to keep compiler quiet */
/*
* We first try to put the tuple on the same page we last inserted a tuple
* on, as cached in the BulkInsertState or relcache entry. If that
* doesn't work, we ask the Free Space Map to locate a suitable page.
* Since the FSM's info might be out of date, we have to be prepared to
* loop around and retry multiple times. (To insure this isn't an infinite
* loop, we must update the FSM with the correct amount of free space on
* each page that proves not to be suitable.) If the FSM has no record of
* a page with enough free space, we give up and extend the relation.
*
* When use_fsm is false, we either put the tuple onto the existing target
* page or extend the relation.
*/
if (len + saveFreeSpace > MaxHeapTupleSize)
{
/* can't fit, don't bother asking FSM */
targetBlock = InvalidBlockNumber;
use_fsm = false;
}
else if (bistate && bistate->current_buf != InvalidBuffer)
targetBlock = BufferGetBlockNumber(bistate->current_buf);
else
targetBlock = RelationGetTargetBlock(relation);
if (targetBlock == InvalidBlockNumber && use_fsm)
{
/*
* We have no cached target page, so ask the FSM for an initial
* target.
*/
targetBlock = GetPageWithFreeSpace(relation, len + saveFreeSpace);
/*
* If the FSM knows nothing of the rel, try the last page before we
* give up and extend. This avoids one-tuple-per-page syndrome during
* bootstrapping or in a recently-started system.
*/
if (targetBlock == InvalidBlockNumber)
{
BlockNumber nblocks = RelationGetNumberOfBlocks(relation);
if (nblocks > 0)
targetBlock = nblocks - 1;
}
}
while (targetBlock != InvalidBlockNumber)
{
/*
* Read and exclusive-lock the target block, as well as the other
* block if one was given, taking suitable care with lock ordering and
* the possibility they are the same block.
*
* If the page-level all-visible flag is set, caller will need to
* clear both that and the corresponding visibility map bit. However,
* by the time we return, we'll have x-locked the buffer, and we don't
* want to do any I/O while in that state. So we check the bit here
* before taking the lock, and pin the page if it appears necessary.
* Checking without the lock creates a risk of getting the wrong
* answer, so we'll have to recheck after acquiring the lock.
*/
if (otherBuffer == InvalidBuffer)
{
/* easy case */
buffer = ReadBufferBI(relation, targetBlock, bistate);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock == targetBlock)
{
/* also easy case */
buffer = otherBuffer;
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock < targetBlock)
{
/* lock other buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else
{
/* lock target buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
}
/*
* We now have the target page (and the other buffer, if any) pinned
* and locked. However, since our initial PageIsAllVisible checks
* were performed before acquiring the lock, the results might now be
* out of date, either for the selected victim buffer, or for the
* other buffer passed by the caller. In that case, we'll need to
* give up our locks, go get the pin(s) we failed to get earlier, and
* re-lock. That's pretty painful, but hopefully shouldn't happen
* often.
*
* Note that there's a small possibility that we didn't pin the page
* above but still have the correct page pinned anyway, either because
* we've already made a previous pass through this loop, or because
* caller passed us the right page anyway.
*
* Note also that it's possible that by the time we get the pin and
* retake the buffer locks, the visibility map bit will have been
* cleared by some other backend anyway. In that case, we'll have
* done a bit of extra work for no gain, but there's no real harm
* done.
*/
if (otherBuffer == InvalidBuffer || buffer <= otherBuffer)
GetVisibilityMapPins(relation, buffer, otherBuffer,
targetBlock, otherBlock, vmbuffer,
vmbuffer_other);
else
GetVisibilityMapPins(relation, otherBuffer, buffer,
otherBlock, targetBlock, vmbuffer_other,
vmbuffer);
/*
* Now we can check to see if there's enough free space here. If so,
* we're done.
*/
page = BufferGetPage(buffer);
pageFreeSpace = PageGetHeapFreeSpace(page);
if (len + saveFreeSpace <= pageFreeSpace)
{
/* use this page as future insert target, too */
RelationSetTargetBlock(relation, targetBlock);
return buffer;
}
/*
* Not enough space, so we must give up our page locks and pin (if
* any) and prepare to look elsewhere. We don't care which order we
* unlock the two buffers in, so this can be slightly simpler than the
* code above.
*/
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
if (otherBuffer == InvalidBuffer)
ReleaseBuffer(buffer);
else if (otherBlock != targetBlock)
{
LockBuffer(otherBuffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
/* Without FSM, always fall out of the loop and extend */
if (!use_fsm)
break;
/*
* Update FSM as to condition of this page, and ask for another page
* to try.
*/
targetBlock = RecordAndGetPageWithFreeSpace(relation,
targetBlock,
pageFreeSpace,
len + saveFreeSpace);
}
/*
* Have to extend the relation.
*
* 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(relation);
if (needLock)
LockRelationForExtension(relation, ExclusiveLock);
/*
* XXX This does an lseek - rather expensive - but at the moment it is the
* only way to accurately determine how many blocks are in a relation. Is
* it worth keeping an accurate file length in shared memory someplace,
* rather than relying on the kernel to do it for us?
*/
buffer = ReadBufferBI(relation, P_NEW, bistate);
/*
* We can be certain that locking the otherBuffer first is OK, since it
* must have a lower page number.
*/
if (otherBuffer != InvalidBuffer)
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
/*
* Now acquire lock on the new page.
*/
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/*
* 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 vacuumlazy.c --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(relation, ExclusiveLock);
/*
* We need to initialize the empty new page. Double-check that it really
* is empty (this should never happen, but if it does we don't want to
* risk wiping out valid data).
*/
page = BufferGetPage(buffer);
if (!PageIsNew(page))
elog(ERROR, "page %u of relation \"%s\" should be empty but is not",
BufferGetBlockNumber(buffer),
RelationGetRelationName(relation));
PageInit(page, BufferGetPageSize(buffer), 0);
if (len > PageGetHeapFreeSpace(page))
{
/* We should not get here given the test at the top */
elog(PANIC, "tuple is too big: size %lu", (unsigned long) len);
}
/*
* Remember the new page as our target for future insertions.
*
* XXX should we enter the new page into the free space map immediately,
* or just keep it for this backend's exclusive use in the short run
* (until VACUUM sees it)? Seems to depend on whether you expect the
* current backend to make more insertions or not, which is probably a
* good bet most of the time. So for now, don't add it to FSM yet.
*/
RelationSetTargetBlock(relation, BufferGetBlockNumber(buffer));
return buffer;
}
Definition at line 36 of file hio.c.
References BufferGetBlockNumber(), BufferGetPage, elog, InvalidOffsetNumber, ItemPointerSet, PageAddItem(), PageGetItem, PageGetItemId, PANIC, HeapTupleData::t_data, HeapTupleData::t_len, and HeapTupleData::t_self.
Referenced by heap_insert(), heap_multi_insert(), and heap_update().
{
Page pageHeader;
OffsetNumber offnum;
ItemId itemId;
Item item;
/* Add the tuple to the page */
pageHeader = BufferGetPage(buffer);
offnum = PageAddItem(pageHeader, (Item) tuple->t_data,
tuple->t_len, InvalidOffsetNumber, false, true);
if (offnum == InvalidOffsetNumber)
elog(PANIC, "failed to add tuple to page");
/* Update tuple->t_self to the actual position where it was stored */
ItemPointerSet(&(tuple->t_self), BufferGetBlockNumber(buffer), offnum);
/* Insert the correct position into CTID of the stored tuple, too */
itemId = PageGetItemId(pageHeader, offnum);
item = PageGetItem(pageHeader, itemId);
((HeapTupleHeader) item)->t_ctid = tuple->t_self;
}
1.7.1