/*
* Release resources associated with a BrinBuildState.
*/
static void
terminate_brin_buildstate(BrinBuildState *state)
{
/*
* Release the last index buffer used. We might as well ensure that
* whatever free space remains in that page is available in FSM, too.
*/
if (!BufferIsInvalid(state->bs_currentInsertBuf))
{
Page page;
Size freespace;
BlockNumber blk;
page = BufferGetPage(state->bs_currentInsertBuf);
freespace = PageGetFreeSpace(page);
blk = BufferGetBlockNumber(state->bs_currentInsertBuf);
ReleaseBuffer(state->bs_currentInsertBuf);
RecordPageWithFreeSpace(state->bs_irel, blk, freespace);
FreeSpaceMapVacuumRange(state->bs_irel, blk, blk + 1);
}
brin_free_desc(state->bs_bdesc);
pfree(state->bs_dtuple);
pfree(state);
}
/*
* Extend a relation by multiple blocks to avoid future contention on the
* relation extension lock. Our goal is to pre-extend the relation by an
* amount which ramps up as the degree of contention ramps up, but limiting
* the result to some sane overall value.
*/
static void
RelationAddExtraBlocks(Relation relation, BulkInsertState bistate)
{
BlockNumber blockNum,
firstBlock = InvalidBlockNumber;
int extraBlocks;
int lockWaiters;
/* Use the length of the lock wait queue to judge how much to extend. */
lockWaiters = RelationExtensionLockWaiterCount(relation);
if (lockWaiters <= 0)
return;
/*
* It might seem like multiplying the number of lock waiters by as much as
* 20 is too aggressive, but benchmarking revealed that smaller numbers
* were insufficient. 512 is just an arbitrary cap to prevent
* pathological results.
*/
extraBlocks = Min(512, lockWaiters * 20);
do
{
Buffer buffer;
Page page;
Size freespace;
/*
* Extend by one page. This should generally match the main-line
* extension code in RelationGetBufferForTuple, except that we hold
* the relation extension lock throughout.
*/
buffer = ReadBufferBI(relation, P_NEW, bistate);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
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);
/*
* We mark all the new buffers dirty, but do nothing to write them
* out; they'll probably get used soon, and even if they are not, a
* crash will leave an okay all-zeroes page on disk.
*/
MarkBufferDirty(buffer);
/* we'll need this info below */
blockNum = BufferGetBlockNumber(buffer);
freespace = PageGetHeapFreeSpace(page);
UnlockReleaseBuffer(buffer);
/* Remember first block number thus added. */
if (firstBlock == InvalidBlockNumber)
firstBlock = blockNum;
/*
* Immediately update the bottom level of the FSM. This has a good
* chance of making this page visible to other concurrently inserting
* backends, and we want that to happen without delay.
*/
RecordPageWithFreeSpace(relation, blockNum, freespace);
}
while (--extraBlocks > 0);
/*
* Updating the upper levels of the free space map is too expensive to do
* for every block, but it's worth doing once at the end to make sure that
* subsequent insertion activity sees all of those nifty free pages we
* just inserted.
*/
FreeSpaceMapVacuumRange(relation, firstBlock, blockNum + 1);
}
/*
* FreeSpaceMapTruncateRel - adjust for truncation of a relation.
*
* 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 FSM again.
*
* nblocks is the new size of the heap.
*/
void
FreeSpaceMapTruncateRel(Relation rel, BlockNumber nblocks)
{
BlockNumber new_nfsmblocks;
FSMAddress first_removed_address;
uint16 first_removed_slot;
Buffer buf;
RelationOpenSmgr(rel);
/*
* If no FSM has been created yet for this relation, there's nothing to
* truncate.
*/
if (!smgrexists(rel->rd_smgr, FSM_FORKNUM))
return;
/* Get the location in the FSM of the first removed heap block */
first_removed_address = fsm_get_location(nblocks, &first_removed_slot);
/*
* Zero out the tail of the last remaining FSM page. If the slot
* representing the first removed heap block is at a page boundary, as the
* first slot on the FSM page that first_removed_address points to, we can
* just truncate that page altogether.
*/
if (first_removed_slot > 0)
{
buf = fsm_readbuf(rel, first_removed_address, false);
if (!BufferIsValid(buf))
return; /* nothing to do; the FSM was already smaller */
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
/* NO EREPORT(ERROR) from here till changes are logged */
START_CRIT_SECTION();
fsm_truncate_avail(BufferGetPage(buf), first_removed_slot);
/*
* Truncation of a relation is WAL-logged at a higher-level, and we
* will be called at WAL replay. But if checksums are enabled, we need
* to still write a WAL record to protect against a torn page, if the
* page is flushed to disk before the truncation WAL record. We cannot
* use MarkBufferDirtyHint here, because that will not dirty the page
* during recovery.
*/
MarkBufferDirty(buf);
if (!InRecovery && RelationNeedsWAL(rel) && XLogHintBitIsNeeded())
log_newpage_buffer(buf, false);
END_CRIT_SECTION();
UnlockReleaseBuffer(buf);
new_nfsmblocks = fsm_logical_to_physical(first_removed_address) + 1;
}
else
{
new_nfsmblocks = fsm_logical_to_physical(first_removed_address);
if (smgrnblocks(rel->rd_smgr, FSM_FORKNUM) <= new_nfsmblocks)
return; /* nothing to do; the FSM was already smaller */
}
/* Truncate the unused FSM pages, and send smgr inval message */
smgrtruncate(rel->rd_smgr, FSM_FORKNUM, new_nfsmblocks);
/*
* We might as well update the local smgr_fsm_nblocks setting.
* smgrtruncate sent an smgr cache inval message, which will cause other
* backends to invalidate their copy of smgr_fsm_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_fsm_nblocks = new_nfsmblocks;
/*
* Update upper-level FSM pages to account for the truncation. This is
* important because the just-truncated pages were likely marked as
* all-free, and would be preferentially selected.
*/
FreeSpaceMapVacuumRange(rel, nblocks, InvalidBlockNumber);
}
