CommandId
HeapTupleHeaderGetCmax(HeapTupleHeader tup)
{
CommandId cid = HeapTupleHeaderGetRawCommandId(tup);
Assert(!(tup->t_infomask & HEAP_MOVED));
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tup)));
if (tup->t_infomask & HEAP_COMBOCID)
return GetRealCmax(cid);
else
return cid;
}
CommandId
HeapTupleHeaderGetCmax(HeapTupleHeader tup)
{
CommandId cid = HeapTupleHeaderGetRawCommandId(tup);
Assert(!(tup->t_infomask & HEAP_MOVED));
/*
* Because GetUpdateXid() performs memory allocations if xmax is a
* multixact we can't Assert() if we're inside a critical section. This
* weakens the check, but not using GetCmax() inside one would complicate
* things too much.
*/
Assert(CritSectionCount > 0 ||
TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tup)));
if (tup->t_infomask & HEAP_COMBOCID)
return GetRealCmax(cid);
else
return cid;
}
/*
* Add a tuple to the new heap.
*
* Visibility information is copied from the original tuple, except that
* we "freeze" very-old tuples. Note that since we scribble on new_tuple,
* it had better be temp storage not a pointer to the original tuple.
*
* state opaque state as returned by begin_heap_rewrite
* old_tuple original tuple in the old heap
* new_tuple new, rewritten tuple to be inserted to new heap
*/
void
rewrite_heap_tuple(RewriteState state,
HeapTuple old_tuple, HeapTuple new_tuple)
{
MemoryContext old_cxt;
ItemPointerData old_tid;
TidHashKey hashkey;
bool found;
bool free_new;
old_cxt = MemoryContextSwitchTo(state->rs_cxt);
/*
* Copy the original tuple's visibility information into new_tuple.
*
* XXX we might later need to copy some t_infomask2 bits, too? Right now,
* we intentionally clear the HOT status bits.
*/
memcpy(&new_tuple->t_data->t_choice.t_heap,
&old_tuple->t_data->t_choice.t_heap,
sizeof(HeapTupleFields));
new_tuple->t_data->t_infomask &= ~HEAP_XACT_MASK;
new_tuple->t_data->t_infomask2 &= ~HEAP2_XACT_MASK;
new_tuple->t_data->t_infomask |=
old_tuple->t_data->t_infomask & HEAP_XACT_MASK;
/*
* While we have our hands on the tuple, we may as well freeze any
* eligible xmin or xmax, so that future VACUUM effort can be saved.
*/
heap_freeze_tuple(new_tuple->t_data, state->rs_freeze_xid,
state->rs_cutoff_multi);
/*
* Invalid ctid means that ctid should point to the tuple itself. We'll
* override it later if the tuple is part of an update chain.
*/
ItemPointerSetInvalid(&new_tuple->t_data->t_ctid);
/*
* If the tuple has been updated, check the old-to-new mapping hash table.
*/
if (!((old_tuple->t_data->t_infomask & HEAP_XMAX_INVALID) ||
HeapTupleHeaderIsOnlyLocked(old_tuple->t_data)) &&
!(ItemPointerEquals(&(old_tuple->t_self),
&(old_tuple->t_data->t_ctid))))
{
OldToNewMapping mapping;
memset(&hashkey, 0, sizeof(hashkey));
hashkey.xmin = HeapTupleHeaderGetUpdateXid(old_tuple->t_data);
hashkey.tid = old_tuple->t_data->t_ctid;
mapping = (OldToNewMapping)
hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_FIND, NULL);
if (mapping != NULL)
{
/*
* We've already copied the tuple that t_ctid points to, so we can
* set the ctid of this tuple to point to the new location, and
* insert it right away.
*/
new_tuple->t_data->t_ctid = mapping->new_tid;
/* We don't need the mapping entry anymore */
hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_REMOVE, &found);
Assert(found);
}
else
{
/*
* We haven't seen the tuple t_ctid points to yet. Stash this
* tuple into unresolved_tups to be written later.
*/
UnresolvedTup unresolved;
unresolved = hash_search(state->rs_unresolved_tups, &hashkey,
HASH_ENTER, &found);
Assert(!found);
unresolved->old_tid = old_tuple->t_self;
unresolved->tuple = heap_copytuple(new_tuple);
/*
* We can't do anything more now, since we don't know where the
* tuple will be written.
*/
MemoryContextSwitchTo(old_cxt);
return;
}
}
/*
* Now we will write the tuple, and then check to see if it is the B tuple
* in any new or known pair. When we resolve a known pair, we will be
* able to write that pair's A tuple, and then we have to check if it
* resolves some other pair. Hence, we need a loop here.
*/
old_tid = old_tuple->t_self;
free_new = false;
for (;;)
{
ItemPointerData new_tid;
/* Insert the tuple and find out where it's put in new_heap */
raw_heap_insert(state, new_tuple);
new_tid = new_tuple->t_self;
/*
* If the tuple is the updated version of a row, and the prior version
* wouldn't be DEAD yet, then we need to either resolve the prior
* version (if it's waiting in rs_unresolved_tups), or make an entry
* in rs_old_new_tid_map (so we can resolve it when we do see it). The
* previous tuple's xmax would equal this one's xmin, so it's
* RECENTLY_DEAD if and only if the xmin is not before OldestXmin.
*/
if ((new_tuple->t_data->t_infomask & HEAP_UPDATED) &&
!TransactionIdPrecedes(HeapTupleHeaderGetXmin(new_tuple->t_data),
state->rs_oldest_xmin))
{
/*
* Okay, this is B in an update pair. See if we've seen A.
*/
UnresolvedTup unresolved;
memset(&hashkey, 0, sizeof(hashkey));
hashkey.xmin = HeapTupleHeaderGetXmin(new_tuple->t_data);
hashkey.tid = old_tid;
unresolved = hash_search(state->rs_unresolved_tups, &hashkey,
HASH_FIND, NULL);
if (unresolved != NULL)
{
/*
* We have seen and memorized the previous tuple already. Now
* that we know where we inserted the tuple its t_ctid points
* to, fix its t_ctid and insert it to the new heap.
*/
if (free_new)
heap_freetuple(new_tuple);
new_tuple = unresolved->tuple;
free_new = true;
old_tid = unresolved->old_tid;
new_tuple->t_data->t_ctid = new_tid;
/*
* We don't need the hash entry anymore, but don't free its
* tuple just yet.
*/
hash_search(state->rs_unresolved_tups, &hashkey,
HASH_REMOVE, &found);
Assert(found);
/* loop back to insert the previous tuple in the chain */
continue;
}
else
{
/*
* Remember the new tid of this tuple. We'll use it to set the
* ctid when we find the previous tuple in the chain.
*/
OldToNewMapping mapping;
mapping = hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_ENTER, &found);
Assert(!found);
mapping->new_tid = new_tid;
}
}
/* Done with this (chain of) tuples, for now */
if (free_new)
heap_freetuple(new_tuple);
break;
}
MemoryContextSwitchTo(old_cxt);
}
/*
* For all items in this page, find their respective root line pointers.
* If item k is part of a HOT-chain with root at item j, then we set
* root_offsets[k - 1] = j.
*
* The passed-in root_offsets array must have MaxHeapTuplesPerPage entries.
* We zero out all unused entries.
*
* The function must be called with at least share lock on the buffer, to
* prevent concurrent prune operations.
*
* Note: The information collected here is valid only as long as the caller
* holds a pin on the buffer. Once pin is released, a tuple might be pruned
* and reused by a completely unrelated tuple.
*/
void
heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
{
OffsetNumber offnum,
maxoff;
MemSet(root_offsets, 0, MaxHeapTuplesPerPage * sizeof(OffsetNumber));
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
{
ItemId lp = PageGetItemId(page, offnum);
HeapTupleHeader htup;
OffsetNumber nextoffnum;
TransactionId priorXmax;
/* skip unused and dead items */
if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
continue;
if (ItemIdIsNormal(lp))
{
htup = (HeapTupleHeader) PageGetItem(page, lp);
/*
* Check if this tuple is part of a HOT-chain rooted at some other
* tuple. If so, skip it for now; we'll process it when we find
* its root.
*/
if (HeapTupleHeaderIsHeapOnly(htup))
continue;
/*
* This is either a plain tuple or the root of a HOT-chain.
* Remember it in the mapping.
*/
root_offsets[offnum - 1] = offnum;
/* If it's not the start of a HOT-chain, we're done with it */
if (!HeapTupleHeaderIsHotUpdated(htup))
continue;
/* Set up to scan the HOT-chain */
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
else
{
/* Must be a redirect item. We do not set its root_offsets entry */
Assert(ItemIdIsRedirected(lp));
/* Set up to scan the HOT-chain */
nextoffnum = ItemIdGetRedirect(lp);
priorXmax = InvalidTransactionId;
}
/*
* Now follow the HOT-chain and collect other tuples in the chain.
*
* Note: Even though this is a nested loop, the complexity of the
* function is O(N) because a tuple in the page should be visited not
* more than twice, once in the outer loop and once in HOT-chain
* chases.
*/
for (;;)
{
lp = PageGetItemId(page, nextoffnum);
/* Check for broken chains */
if (!ItemIdIsNormal(lp))
break;
htup = (HeapTupleHeader) PageGetItem(page, lp);
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
break;
/* Remember the root line pointer for this item */
root_offsets[nextoffnum - 1] = offnum;
/* Advance to next chain member, if any */
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
}
}
/*
* Prune specified item pointer or a HOT chain originating at that item.
*
* If the item is an index-referenced tuple (i.e. not a heap-only tuple),
* the HOT chain is pruned by removing all DEAD tuples at the start of the HOT
* chain. We also prune any RECENTLY_DEAD tuples preceding a DEAD tuple.
* This is OK because a RECENTLY_DEAD tuple preceding a DEAD tuple is really
* DEAD, the OldestXmin test is just too coarse to detect it.
*
* The root line pointer is redirected to the tuple immediately after the
* latest DEAD tuple. If all tuples in the chain are DEAD, the root line
* pointer is marked LP_DEAD. (This includes the case of a DEAD simple
* tuple, which we treat as a chain of length 1.)
*
* OldestXmin is the cutoff XID used to identify dead tuples.
*
* We don't actually change the page here, except perhaps for hint-bit updates
* caused by HeapTupleSatisfiesVacuum. We just add entries to the arrays in
* prstate showing the changes to be made. Items to be redirected are added
* to the redirected[] array (two entries per redirection); items to be set to
* LP_DEAD state are added to nowdead[]; and items to be set to LP_UNUSED
* state are added to nowunused[].
*
* Returns the number of tuples (to be) deleted from the page.
*/
static int
heap_prune_chain(Relation relation, Buffer buffer, OffsetNumber rootoffnum,
TransactionId OldestXmin,
PruneState *prstate)
{
int ndeleted = 0;
Page dp = (Page) BufferGetPage(buffer);
TransactionId priorXmax = InvalidTransactionId;
ItemId rootlp;
HeapTupleHeader htup;
OffsetNumber latestdead = InvalidOffsetNumber,
maxoff = PageGetMaxOffsetNumber(dp),
offnum;
OffsetNumber chainitems[MaxHeapTuplesPerPage];
int nchain = 0,
i;
rootlp = PageGetItemId(dp, rootoffnum);
/*
* If it's a heap-only tuple, then it is not the start of a HOT chain.
*/
if (ItemIdIsNormal(rootlp))
{
htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
if (HeapTupleHeaderIsHeapOnly(htup))
{
/*
* If the tuple is DEAD and doesn't chain to anything else, mark
* it unused immediately. (If it does chain, we can only remove
* it as part of pruning its chain.)
*
* We need this primarily to handle aborted HOT updates, that is,
* XMIN_INVALID heap-only tuples. Those might not be linked to by
* any chain, since the parent tuple might be re-updated before
* any pruning occurs. So we have to be able to reap them
* separately from chain-pruning. (Note that
* HeapTupleHeaderIsHotUpdated will never return true for an
* XMIN_INVALID tuple, so this code will work even when there were
* sequential updates within the aborted transaction.)
*
* Note that we might first arrive at a dead heap-only tuple
* either here or while following a chain below. Whichever path
* gets there first will mark the tuple unused.
*/
if (HeapTupleSatisfiesVacuum(htup, OldestXmin, buffer)
== HEAPTUPLE_DEAD && !HeapTupleHeaderIsHotUpdated(htup))
{
heap_prune_record_unused(prstate, rootoffnum);
HeapTupleHeaderAdvanceLatestRemovedXid(htup,
&prstate->latestRemovedXid);
ndeleted++;
}
/* Nothing more to do */
return ndeleted;
}
}
/* Start from the root tuple */
offnum = rootoffnum;
/* while not end of the chain */
for (;;)
{
ItemId lp;
bool tupdead,
recent_dead;
/* Some sanity checks */
if (offnum < FirstOffsetNumber || offnum > maxoff)
break;
/* If item is already processed, stop --- it must not be same chain */
if (prstate->marked[offnum])
break;
lp = PageGetItemId(dp, offnum);
/* Unused item obviously isn't part of the chain */
if (!ItemIdIsUsed(lp))
break;
/*
* If we are looking at the redirected root line pointer, jump to the
* first normal tuple in the chain. If we find a redirect somewhere
* else, stop --- it must not be same chain.
*/
if (ItemIdIsRedirected(lp))
{
if (nchain > 0)
break; /* not at start of chain */
chainitems[nchain++] = offnum;
offnum = ItemIdGetRedirect(rootlp);
continue;
}
/*
* Likewise, a dead item pointer can't be part of the chain. (We
* already eliminated the case of dead root tuple outside this
* function.)
*/
if (ItemIdIsDead(lp))
break;
Assert(ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(dp, lp);
/*
* Check the tuple XMIN against prior XMAX, if any
*/
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
/*
* OK, this tuple is indeed a member of the chain.
*/
chainitems[nchain++] = offnum;
/*
* Check tuple's visibility status.
*/
tupdead = recent_dead = false;
switch (HeapTupleSatisfiesVacuum(htup, OldestXmin, buffer))
{
case HEAPTUPLE_DEAD:
tupdead = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
recent_dead = true;
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetUpdateXid(htup));
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* This tuple may soon become DEAD. Update the hint field
* so that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetUpdateXid(htup));
break;
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* If we wanted to optimize for aborts, we might consider
* marking the page prunable when we see INSERT_IN_PROGRESS.
* But we don't. See related decisions about when to mark the
* page prunable in heapam.c.
*/
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
/*
* Remember the last DEAD tuple seen. We will advance past
* RECENTLY_DEAD tuples just in case there's a DEAD one after them;
* but we can't advance past anything else. (XXX is it really worth
* continuing to scan beyond RECENTLY_DEAD? The case where we will
* find another DEAD tuple is a fairly unusual corner case.)
*/
if (tupdead)
{
latestdead = offnum;
HeapTupleHeaderAdvanceLatestRemovedXid(htup,
&prstate->latestRemovedXid);
}
else if (!recent_dead)
break;
/*
* If the tuple is not HOT-updated, then we are at the end of this
* HOT-update chain.
*/
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/*
* Advance to next chain member.
*/
Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
/*
* If we found a DEAD tuple in the chain, adjust the HOT chain so that all
* the DEAD tuples at the start of the chain are removed and the root line
* pointer is appropriately redirected.
*/
if (OffsetNumberIsValid(latestdead))
{
/*
* Mark as unused each intermediate item that we are able to remove
* from the chain.
*
* When the previous item is the last dead tuple seen, we are at the
* right candidate for redirection.
*/
for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
{
heap_prune_record_unused(prstate, chainitems[i]);
ndeleted++;
}
/*
* If the root entry had been a normal tuple, we are deleting it, so
* count it in the result. But changing a redirect (even to DEAD
* state) doesn't count.
*/
if (ItemIdIsNormal(rootlp))
ndeleted++;
/*
* If the DEAD tuple is at the end of the chain, the entire chain is
* dead and the root line pointer can be marked dead. Otherwise just
* redirect the root to the correct chain member.
*/
if (i >= nchain)
heap_prune_record_dead(prstate, rootoffnum);
else
heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
}
else if (nchain < 2 && ItemIdIsRedirected(rootlp))
{
/*
* We found a redirect item that doesn't point to a valid follow-on
* item. This can happen if the loop in heap_page_prune caused us to
* visit the dead successor of a redirect item before visiting the
* redirect item. We can clean up by setting the redirect item to
* DEAD state.
*/
heap_prune_record_dead(prstate, rootoffnum);
}
return ndeleted;
}