#include "postgres.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/transam.h"
#include "access/htup_details.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "utils/rel.h"
#include "utils/tqual.h"
Go to the source code of this file.
Data Structures | |
struct | PruneState |
Functions | |
static int | heap_prune_chain (Relation relation, Buffer buffer, OffsetNumber rootoffnum, TransactionId OldestXmin, PruneState *prstate) |
static void | heap_prune_record_prunable (PruneState *prstate, TransactionId xid) |
static void | heap_prune_record_redirect (PruneState *prstate, OffsetNumber offnum, OffsetNumber rdoffnum) |
static void | heap_prune_record_dead (PruneState *prstate, OffsetNumber offnum) |
static void | heap_prune_record_unused (PruneState *prstate, OffsetNumber offnum) |
void | heap_page_prune_opt (Relation relation, Buffer buffer, TransactionId OldestXmin) |
int | heap_page_prune (Relation relation, Buffer buffer, TransactionId OldestXmin, bool report_stats, TransactionId *latestRemovedXid) |
void | heap_page_prune_execute (Buffer buffer, OffsetNumber *redirected, int nredirected, OffsetNumber *nowdead, int ndead, OffsetNumber *nowunused, int nunused) |
void | heap_get_root_tuples (Page page, OffsetNumber *root_offsets) |
void heap_get_root_tuples | ( | Page | page, | |
OffsetNumber * | root_offsets | |||
) |
Definition at line 705 of file pruneheap.c.
References Assert, FirstOffsetNumber, HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetOffsetNumber, MaxHeapTuplesPerPage, MemSet, OffsetNumberNext, PageGetItem, PageGetItemId, PageGetMaxOffsetNumber, HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.
Referenced by IndexBuildHeapScan(), and validate_index_heapscan().
{ 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); } } }
int heap_page_prune | ( | Relation | relation, | |
Buffer | buffer, | |||
TransactionId | OldestXmin, | |||
bool | report_stats, | |||
TransactionId * | latestRemovedXid | |||
) |
Definition at line 155 of file pruneheap.c.
References BufferGetPage, END_CRIT_SECTION, FirstOffsetNumber, heap_page_prune_execute(), heap_prune_chain(), ItemIdIsDead, ItemIdIsUsed, PruneState::latestRemovedXid, log_heap_clean(), MarkBufferDirty(), MarkBufferDirtyHint(), PruneState::marked, PruneState::ndead, PruneState::new_prune_xid, PruneState::nowdead, PruneState::nowunused, PruneState::nredirected, PruneState::nunused, OffsetNumberNext, PageClearFull, PageGetItemId, PageGetMaxOffsetNumber, PageIsFull, PageSetLSN, pgstat_update_heap_dead_tuples(), PruneState::redirected, RelationNeedsWAL, and START_CRIT_SECTION.
Referenced by heap_page_prune_opt(), and lazy_scan_heap().
{ int ndeleted = 0; Page page = BufferGetPage(buffer); OffsetNumber offnum, maxoff; PruneState prstate; /* * Our strategy is to scan the page and make lists of items to change, * then apply the changes within a critical section. This keeps as much * logic as possible out of the critical section, and also ensures that * WAL replay will work the same as the normal case. * * First, initialize the new pd_prune_xid value to zero (indicating no * prunable tuples). If we find any tuples which may soon become * prunable, we will save the lowest relevant XID in new_prune_xid. Also * initialize the rest of our working state. */ prstate.new_prune_xid = InvalidTransactionId; prstate.latestRemovedXid = *latestRemovedXid; prstate.nredirected = prstate.ndead = prstate.nunused = 0; memset(prstate.marked, 0, sizeof(prstate.marked)); /* Scan the page */ maxoff = PageGetMaxOffsetNumber(page); for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum)) { ItemId itemid; /* Ignore items already processed as part of an earlier chain */ if (prstate.marked[offnum]) continue; /* Nothing to do if slot is empty or already dead */ itemid = PageGetItemId(page, offnum); if (!ItemIdIsUsed(itemid) || ItemIdIsDead(itemid)) continue; /* Process this item or chain of items */ ndeleted += heap_prune_chain(relation, buffer, offnum, OldestXmin, &prstate); } /* Any error while applying the changes is critical */ START_CRIT_SECTION(); /* Have we found any prunable items? */ if (prstate.nredirected > 0 || prstate.ndead > 0 || prstate.nunused > 0) { /* * Apply the planned item changes, then repair page fragmentation, and * update the page's hint bit about whether it has free line pointers. */ heap_page_prune_execute(buffer, prstate.redirected, prstate.nredirected, prstate.nowdead, prstate.ndead, prstate.nowunused, prstate.nunused); /* * Update the page's pd_prune_xid field to either zero, or the lowest * XID of any soon-prunable tuple. */ ((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid; /* * Also clear the "page is full" flag, since there's no point in * repeating the prune/defrag process until something else happens to * the page. */ PageClearFull(page); MarkBufferDirty(buffer); /* * Emit a WAL HEAP_CLEAN record showing what we did */ if (RelationNeedsWAL(relation)) { XLogRecPtr recptr; recptr = log_heap_clean(relation, buffer, prstate.redirected, prstate.nredirected, prstate.nowdead, prstate.ndead, prstate.nowunused, prstate.nunused, prstate.latestRemovedXid); PageSetLSN(BufferGetPage(buffer), recptr); } } else { /* * If we didn't prune anything, but have found a new value for the * pd_prune_xid field, update it and mark the buffer dirty. This is * treated as a non-WAL-logged hint. * * Also clear the "page is full" flag if it is set, since there's no * point in repeating the prune/defrag process until something else * happens to the page. */ if (((PageHeader) page)->pd_prune_xid != prstate.new_prune_xid || PageIsFull(page)) { ((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid; PageClearFull(page); MarkBufferDirtyHint(buffer); } } END_CRIT_SECTION(); /* * If requested, report the number of tuples reclaimed to pgstats. This is * ndeleted minus ndead, because we don't want to count a now-DEAD root * item as a deletion for this purpose. */ if (report_stats && ndeleted > prstate.ndead) pgstat_update_heap_dead_tuples(relation, ndeleted - prstate.ndead); *latestRemovedXid = prstate.latestRemovedXid; /* * XXX Should we update the FSM information of this page ? * * There are two schools of thought here. We may not want to update FSM * information so that the page is not used for unrelated UPDATEs/INSERTs * and any free space in this page will remain available for further * UPDATEs in *this* page, thus improving chances for doing HOT updates. * * But for a large table and where a page does not receive further UPDATEs * for a long time, we might waste this space by not updating the FSM * information. The relation may get extended and fragmented further. * * One possibility is to leave "fillfactor" worth of space in this page * and update FSM with the remaining space. */ return ndeleted; }
void heap_page_prune_execute | ( | Buffer | buffer, | |
OffsetNumber * | redirected, | |||
int | nredirected, | |||
OffsetNumber * | nowdead, | |||
int | ndead, | |||
OffsetNumber * | nowunused, | |||
int | nunused | |||
) |
Definition at line 641 of file pruneheap.c.
References BufferGetPage, i, ItemIdSetDead, ItemIdSetRedirect, ItemIdSetUnused, PageGetItemId, and PageRepairFragmentation().
Referenced by heap_page_prune(), and heap_xlog_clean().
{ Page page = (Page) BufferGetPage(buffer); OffsetNumber *offnum; int i; /* Update all redirected line pointers */ offnum = redirected; for (i = 0; i < nredirected; i++) { OffsetNumber fromoff = *offnum++; OffsetNumber tooff = *offnum++; ItemId fromlp = PageGetItemId(page, fromoff); ItemIdSetRedirect(fromlp, tooff); } /* Update all now-dead line pointers */ offnum = nowdead; for (i = 0; i < ndead; i++) { OffsetNumber off = *offnum++; ItemId lp = PageGetItemId(page, off); ItemIdSetDead(lp); } /* Update all now-unused line pointers */ offnum = nowunused; for (i = 0; i < nunused; i++) { OffsetNumber off = *offnum++; ItemId lp = PageGetItemId(page, off); ItemIdSetUnused(lp); } /* * Finally, repair any fragmentation, and update the page's hint bit about * whether it has free pointers. */ PageRepairFragmentation(page); }
void heap_page_prune_opt | ( | Relation | relation, | |
Buffer | buffer, | |||
TransactionId | OldestXmin | |||
) |
Definition at line 73 of file pruneheap.c.
References BUFFER_LOCK_UNLOCK, BufferGetPage, ConditionalLockBufferForCleanup(), HEAP_DEFAULT_FILLFACTOR, heap_page_prune(), LockBuffer(), Max, PageGetHeapFreeSpace(), PageIsFull, PageIsPrunable, RecoveryInProgress(), and RelationGetTargetPageFreeSpace.
Referenced by bitgetpage(), heapgetpage(), and index_fetch_heap().
{ Page page = BufferGetPage(buffer); Size minfree; /* * Let's see if we really need pruning. * * Forget it if page is not hinted to contain something prunable that's * older than OldestXmin. */ if (!PageIsPrunable(page, OldestXmin)) return; /* * We can't write WAL in recovery mode, so there's no point trying to * clean the page. The master will likely issue a cleaning WAL record soon * anyway, so this is no particular loss. */ if (RecoveryInProgress()) return; /* * We prune when a previous UPDATE failed to find enough space on the page * for a new tuple version, or when free space falls below the relation's * fill-factor target (but not less than 10%). * * Checking free space here is questionable since we aren't holding any * lock on the buffer; in the worst case we could get a bogus answer. It's * unlikely to be *seriously* wrong, though, since reading either pd_lower * or pd_upper is probably atomic. Avoiding taking a lock seems more * important than sometimes getting a wrong answer in what is after all * just a heuristic estimate. */ minfree = RelationGetTargetPageFreeSpace(relation, HEAP_DEFAULT_FILLFACTOR); minfree = Max(minfree, BLCKSZ / 10); if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree) { /* OK, try to get exclusive buffer lock */ if (!ConditionalLockBufferForCleanup(buffer)) return; /* * Now that we have buffer lock, get accurate information about the * page's free space, and recheck the heuristic about whether to * prune. (We needn't recheck PageIsPrunable, since no one else could * have pruned while we hold pin.) */ if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree) { TransactionId ignore = InvalidTransactionId; /* return value not * needed */ /* OK to prune */ (void) heap_page_prune(relation, buffer, OldestXmin, true, &ignore); } /* And release buffer lock */ LockBuffer(buffer, BUFFER_LOCK_UNLOCK); } }
static int heap_prune_chain | ( | Relation | relation, | |
Buffer | buffer, | |||
OffsetNumber | rootoffnum, | |||
TransactionId | OldestXmin, | |||
PruneState * | prstate | |||
) | [static] |
Definition at line 327 of file pruneheap.c.
References Assert, BufferGetBlockNumber(), BufferGetPage, elog, ERROR, heap_prune_record_dead(), heap_prune_record_prunable(), heap_prune_record_redirect(), heap_prune_record_unused(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderAdvanceLatestRemovedXid(), HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, HeapTupleSatisfiesVacuum(), i, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetBlockNumber, ItemPointerGetOffsetNumber, PruneState::latestRemovedXid, PruneState::marked, OffsetNumberIsValid, PageGetItem, PageGetItemId, PageGetMaxOffsetNumber, HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.
Referenced by heap_page_prune().
{ 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; }
static void heap_prune_record_dead | ( | PruneState * | prstate, | |
OffsetNumber | offnum | |||
) | [static] |
Definition at line 610 of file pruneheap.c.
References Assert, PruneState::marked, MaxHeapTuplesPerPage, PruneState::ndead, and PruneState::nowdead.
Referenced by heap_prune_chain().
static void heap_prune_record_prunable | ( | PruneState * | prstate, | |
TransactionId | xid | |||
) | [static] |
Definition at line 581 of file pruneheap.c.
References Assert, PruneState::new_prune_xid, TransactionIdIsNormal, TransactionIdIsValid, and TransactionIdPrecedes().
Referenced by heap_prune_chain().
{ /* * This should exactly match the PageSetPrunable macro. We can't store * directly into the page header yet, so we update working state. */ Assert(TransactionIdIsNormal(xid)); if (!TransactionIdIsValid(prstate->new_prune_xid) || TransactionIdPrecedes(xid, prstate->new_prune_xid)) prstate->new_prune_xid = xid; }
static void heap_prune_record_redirect | ( | PruneState * | prstate, | |
OffsetNumber | offnum, | |||
OffsetNumber | rdoffnum | |||
) | [static] |
Definition at line 595 of file pruneheap.c.
References Assert, PruneState::marked, MaxHeapTuplesPerPage, PruneState::nredirected, and PruneState::redirected.
Referenced by heap_prune_chain().
{ Assert(prstate->nredirected < MaxHeapTuplesPerPage); prstate->redirected[prstate->nredirected * 2] = offnum; prstate->redirected[prstate->nredirected * 2 + 1] = rdoffnum; prstate->nredirected++; Assert(!prstate->marked[offnum]); prstate->marked[offnum] = true; Assert(!prstate->marked[rdoffnum]); prstate->marked[rdoffnum] = true; }
static void heap_prune_record_unused | ( | PruneState * | prstate, | |
OffsetNumber | offnum | |||
) | [static] |
Definition at line 621 of file pruneheap.c.
References Assert, PruneState::marked, MaxHeapTuplesPerPage, PruneState::nowunused, and PruneState::nunused.
Referenced by heap_prune_chain().