From be9b33339f0494ffd3b2327322433bacf72a5428 Mon Sep 17 00:00:00 2001 From: Peter Geoghegan Date: Mon, 22 Nov 2021 10:02:30 -0800 Subject: [PATCH v5 4/5] Loosen coupling between relfrozenxid and tuple freezing. Stop using tuple freezing (and MultiXact freezing) tuple header cutoffs to determine the final relfrozenxid (and relminmxid) values that we set for heap relations in pg_class. Use "optimal" values instead. Optimal values are the most recent values that are less than or equal to any remaining XID/MultiXact in a tuple header (not counting frozen xmin/xmax values). This is now kept track of by VACUUM. "Optimal" values are always >= the tuple header FreezeLimit in an aggressive VACUUM. For a non-aggressive VACUUM, they can be less than or greater than the tuple header FreezeLimit cutoff (though we still often pass invalid values to indicate that we cannot advance relfrozenxid during the VACUUM). --- src/include/access/heapam.h | 4 +- src/include/access/heapam_xlog.h | 4 +- src/include/commands/vacuum.h | 1 + src/backend/access/heap/heapam.c | 186 ++++++++++++++++++++------- src/backend/access/heap/vacuumlazy.c | 78 +++++++---- src/backend/commands/cluster.c | 5 +- src/backend/commands/vacuum.c | 34 ++++- 7 files changed, 231 insertions(+), 81 deletions(-) diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index f3fb1e93a..bc5a96796 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -168,7 +168,9 @@ extern bool heap_freeze_tuple(HeapTupleHeader tuple, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId cutoff_xid, TransactionId cutoff_multi); extern bool heap_tuple_needs_freeze(HeapTupleHeader tuple, TransactionId cutoff_xid, - MultiXactId cutoff_multi, Buffer buf); + MultiXactId cutoff_multi, + TransactionId *NewRelfrozenxid, + MultiXactId *NewRelminmxid, Buffer buf); extern bool heap_tuple_needs_eventual_freeze(HeapTupleHeader tuple); extern void simple_heap_insert(Relation relation, HeapTuple tup); diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h index ab9e873bc..b0ede623e 100644 --- a/src/include/access/heapam_xlog.h +++ b/src/include/access/heapam_xlog.h @@ -410,7 +410,9 @@ extern bool heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid, TransactionId cutoff_multi, xl_heap_freeze_tuple *frz, - bool *totally_frozen); + bool *totally_frozen, + TransactionId *NewRelfrozenxid, + MultiXactId *NewRelminmxid); extern void heap_execute_freeze_tuple(HeapTupleHeader tuple, xl_heap_freeze_tuple *xlrec_tp); extern XLogRecPtr log_heap_visible(RelFileNode rnode, Buffer heap_buffer, diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index 1848a65df..db813af99 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -291,6 +291,7 @@ extern bool vacuum_set_xid_limits(Relation rel, int multixact_freeze_min_age, int multixact_freeze_table_age, TransactionId *oldestXmin, + MultiXactId *oldestMxact, TransactionId *freezeLimit, MultiXactId *multiXactCutoff); extern bool vacuum_xid_failsafe_check(TransactionId relfrozenxid, diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index a1bacb0eb..2f3399265 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -6087,12 +6087,24 @@ heap_inplace_update(Relation relation, HeapTuple tuple) * FRM_RETURN_IS_MULTI * The return value is a new MultiXactId to set as new Xmax. * (caller must obtain proper infomask bits using GetMultiXactIdHintBits) + * + * "NewRelfrozenxid" is an output value; it's used to maintain target new + * relfrozenxid for the relation. It can be ignored unless "flags" contains + * either FRM_NOOP or FRM_RETURN_IS_MULTI, because we only handle multiXacts + * here. This follows the general convention: only track XIDs that will still + * be in the table after the ongoing VACUUM finishes. Note that it's up to + * caller to maintain this when the Xid return value is itself an Xid. + * + * Note that we cannot depend on xmin to maintain NewRelfrozenxid. We need to + * push maintenance of NewRelfrozenxid down this far, since in general xmin + * might have been frozen by an earlier VACUUM operation, in which case our + * caller will not have factored-in xmin when maintaining NewRelfrozenxid. */ static TransactionId FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId cutoff_xid, MultiXactId cutoff_multi, - uint16 *flags) + uint16 *flags, TransactionId *NewRelfrozenxid) { TransactionId xid = InvalidTransactionId; int i; @@ -6104,6 +6116,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, bool has_lockers; TransactionId update_xid; bool update_committed; + TransactionId tempNewRelfrozenxid; *flags = 0; @@ -6198,13 +6211,13 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, /* is there anything older than the cutoff? */ need_replace = false; + tempNewRelfrozenxid = *NewRelfrozenxid; for (i = 0; i < nmembers; i++) { if (TransactionIdPrecedes(members[i].xid, cutoff_xid)) - { need_replace = true; - break; - } + if (TransactionIdPrecedes(members[i].xid, tempNewRelfrozenxid)) + tempNewRelfrozenxid = members[i].xid; } /* @@ -6213,6 +6226,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, */ if (!need_replace) { + *NewRelfrozenxid = tempNewRelfrozenxid; *flags |= FRM_NOOP; pfree(members); return InvalidTransactionId; @@ -6222,6 +6236,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, * If the multi needs to be updated, figure out which members do we need * to keep. */ + tempNewRelfrozenxid = *NewRelfrozenxid; nnewmembers = 0; newmembers = palloc(sizeof(MultiXactMember) * nmembers); has_lockers = false; @@ -6303,7 +6318,11 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, * list.) */ if (TransactionIdIsValid(update_xid)) + { newmembers[nnewmembers++] = members[i]; + if (TransactionIdPrecedes(members[i].xid, tempNewRelfrozenxid)) + tempNewRelfrozenxid = members[i].xid; + } } else { @@ -6313,6 +6332,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, { /* running locker cannot possibly be older than the cutoff */ Assert(!TransactionIdPrecedes(members[i].xid, cutoff_xid)); + Assert(!TransactionIdPrecedes(members[i].xid, *NewRelfrozenxid)); newmembers[nnewmembers++] = members[i]; has_lockers = true; } @@ -6341,6 +6361,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, if (update_committed) *flags |= FRM_MARK_COMMITTED; xid = update_xid; + /* Caller manages NewRelfrozenxid directly when we return an XID */ } else { @@ -6350,6 +6371,7 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, */ xid = MultiXactIdCreateFromMembers(nnewmembers, newmembers); *flags |= FRM_RETURN_IS_MULTI; + *NewRelfrozenxid = tempNewRelfrozenxid; } pfree(newmembers); @@ -6368,6 +6390,13 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask, * will be totally frozen after these operations are performed and false if * more freezing will eventually be required. * + * Also maintains *NewRelfrozenxid and *NewRelminmxid, which are the current + * target relfrozenxid and relminmxid for the relation. Assumption is that + * caller will actually go on to freeze as indicated by our *frz output, so + * any (xmin, xmax, xvac) XIDs that we indicate need to be frozen won't need + * to be counted here. Values are valid lower bounds at the point that the + * ongoing VACUUM finishes. + * * Caller is responsible for setting the offset field, if appropriate. * * It is assumed that the caller has checked the tuple with @@ -6392,7 +6421,9 @@ bool heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId cutoff_xid, TransactionId cutoff_multi, - xl_heap_freeze_tuple *frz, bool *totally_frozen_p) + xl_heap_freeze_tuple *frz, bool *totally_frozen_p, + TransactionId *NewRelfrozenxid, + MultiXactId *NewRelminmxid) { bool changed = false; bool xmax_already_frozen = false; @@ -6436,6 +6467,11 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, frz->t_infomask |= HEAP_XMIN_FROZEN; changed = true; } + else if (TransactionIdPrecedes(xid, *NewRelfrozenxid)) + { + /* won't be frozen, but older than current NewRelfrozenxid */ + *NewRelfrozenxid = xid; + } } /* @@ -6453,10 +6489,11 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, { TransactionId newxmax; uint16 flags; + TransactionId temp = *NewRelfrozenxid; newxmax = FreezeMultiXactId(xid, tuple->t_infomask, relfrozenxid, relminmxid, - cutoff_xid, cutoff_multi, &flags); + cutoff_xid, cutoff_multi, &flags, &temp); freeze_xmax = (flags & FRM_INVALIDATE_XMAX); @@ -6474,6 +6511,24 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, if (flags & FRM_MARK_COMMITTED) frz->t_infomask |= HEAP_XMAX_COMMITTED; changed = true; + + if (TransactionIdPrecedes(newxmax, *NewRelfrozenxid)) + { + /* New xmax is an XID older than new NewRelfrozenxid */ + *NewRelfrozenxid = newxmax; + } + } + else if (flags & FRM_NOOP) + { + /* + * Changing nothing, so might have to ratchet back NewRelminmxid, + * NewRelfrozenxid, or both together + */ + if (MultiXactIdIsValid(xid) && + MultiXactIdPrecedes(xid, *NewRelminmxid)) + *NewRelminmxid = xid; + if (TransactionIdPrecedes(temp, *NewRelfrozenxid)) + *NewRelfrozenxid = temp; } else if (flags & FRM_RETURN_IS_MULTI) { @@ -6495,6 +6550,13 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, frz->xmax = newxmax; changed = true; + + /* + * New multixact might have remaining XID older than + * NewRelfrozenxid + */ + if (TransactionIdPrecedes(temp, *NewRelfrozenxid)) + *NewRelfrozenxid = temp; } } else if (TransactionIdIsNormal(xid)) @@ -6522,7 +6584,14 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, freeze_xmax = true; } else + { freeze_xmax = false; + if (TransactionIdPrecedes(xid, *NewRelfrozenxid)) + { + /* won't be frozen, but older than current NewRelfrozenxid */ + *NewRelfrozenxid = xid; + } + } } else if ((tuple->t_infomask & HEAP_XMAX_INVALID) || !TransactionIdIsValid(HeapTupleHeaderGetRawXmax(tuple))) @@ -6569,6 +6638,9 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, * was removed in PostgreSQL 9.0. Note that if we were to respect * cutoff_xid here, we'd need to make surely to clear totally_frozen * when we skipped freezing on that basis. + * + * Since we always freeze here, NewRelfrozenxid doesn't need to be + * maintained. */ if (TransactionIdIsNormal(xid)) { @@ -6646,11 +6718,14 @@ heap_freeze_tuple(HeapTupleHeader tuple, xl_heap_freeze_tuple frz; bool do_freeze; bool tuple_totally_frozen; + TransactionId NewRelfrozenxid = FirstNormalTransactionId; + MultiXactId NewRelminmxid = FirstMultiXactId; do_freeze = heap_prepare_freeze_tuple(tuple, relfrozenxid, relminmxid, cutoff_xid, cutoff_multi, - &frz, &tuple_totally_frozen); + &frz, &tuple_totally_frozen, + &NewRelfrozenxid, &NewRelminmxid); /* * Note that because this is not a WAL-logged operation, we don't need to @@ -7080,6 +7155,15 @@ heap_tuple_needs_eventual_freeze(HeapTupleHeader tuple) * Check to see whether any of the XID fields of a tuple (xmin, xmax, xvac) * are older than the specified cutoff XID or MultiXactId. If so, return true. * + * Also maintains *NewRelfrozenxid and *NewRelminmxid, which are the current + * target relfrozenxid and relminmxid for the relation. Assumption is that + * caller will never freeze any of the XIDs from the tuple, even when we say + * that they should. If caller opts to go with our recommendation to freeze, + * then it must account for the fact that it shouldn't trust how we've set + * NewRelfrozenxid/NewRelminmxid. (In practice aggressive VACUUMs always take + * our recommendation because they must, and non-aggressive VACUUMs always opt + * to not freeze, preferring to ratchet back NewRelfrozenxid instead). + * * It doesn't matter whether the tuple is alive or dead, we are checking * to see if a tuple needs to be removed or frozen to avoid wraparound. * @@ -7088,74 +7172,86 @@ heap_tuple_needs_eventual_freeze(HeapTupleHeader tuple) */ bool heap_tuple_needs_freeze(HeapTupleHeader tuple, TransactionId cutoff_xid, - MultiXactId cutoff_multi, Buffer buf) + MultiXactId cutoff_multi, + TransactionId *NewRelfrozenxid, + MultiXactId *NewRelminmxid, Buffer buf) { TransactionId xid; + bool needs_freeze = false; xid = HeapTupleHeaderGetXmin(tuple); - if (TransactionIdIsNormal(xid) && - TransactionIdPrecedes(xid, cutoff_xid)) - return true; + if (TransactionIdIsNormal(xid)) + { + if (TransactionIdPrecedes(xid, *NewRelfrozenxid)) + *NewRelfrozenxid = xid; + if (TransactionIdPrecedes(xid, cutoff_xid)) + needs_freeze = true; + } /* * The considerations for multixacts are complicated; look at * heap_prepare_freeze_tuple for justifications. This routine had better * be in sync with that one! + * + * (Actually, we maintain NewRelminmxid differently here, because we + * assume that XIDs that should be frozen according to cutoff_xid won't + * be, whereas heap_prepare_freeze_tuple makes the opposite assumption.) */ if (tuple->t_infomask & HEAP_XMAX_IS_MULTI) { MultiXactId multi; + MultiXactMember *members; + int nmembers; multi = HeapTupleHeaderGetRawXmax(tuple); - if (!MultiXactIdIsValid(multi)) - { - /* no xmax set, ignore */ - ; - } - else if (HEAP_LOCKED_UPGRADED(tuple->t_infomask)) + if (MultiXactIdIsValid(multi) && + MultiXactIdPrecedes(multi, *NewRelminmxid)) + *NewRelminmxid = multi; + + if (HEAP_LOCKED_UPGRADED(tuple->t_infomask)) return true; else if (MultiXactIdPrecedes(multi, cutoff_multi)) - return true; - else + needs_freeze = true; + + /* need to check whether any member of the mxact is too old */ + nmembers = GetMultiXactIdMembers(multi, &members, false, + HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask)); + + for (int i = 0; i < nmembers; i++) { - MultiXactMember *members; - int nmembers; - int i; - - /* need to check whether any member of the mxact is too old */ - - nmembers = GetMultiXactIdMembers(multi, &members, false, - HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask)); - - for (i = 0; i < nmembers; i++) - { - if (TransactionIdPrecedes(members[i].xid, cutoff_xid)) - { - pfree(members); - return true; - } - } - if (nmembers > 0) - pfree(members); + if (TransactionIdPrecedes(members[i].xid, cutoff_xid)) + needs_freeze = true; + if (TransactionIdPrecedes(members[i].xid, *NewRelfrozenxid)) + *NewRelfrozenxid = xid; } + if (nmembers > 0) + pfree(members); } else { xid = HeapTupleHeaderGetRawXmax(tuple); - if (TransactionIdIsNormal(xid) && - TransactionIdPrecedes(xid, cutoff_xid)) - return true; + if (TransactionIdIsNormal(xid)) + { + if (TransactionIdPrecedes(xid, *NewRelfrozenxid)) + *NewRelfrozenxid = xid; + if (TransactionIdPrecedes(xid, cutoff_xid)) + needs_freeze = true; + } } if (tuple->t_infomask & HEAP_MOVED) { xid = HeapTupleHeaderGetXvac(tuple); - if (TransactionIdIsNormal(xid) && - TransactionIdPrecedes(xid, cutoff_xid)) - return true; + if (TransactionIdIsNormal(xid)) + { + if (TransactionIdPrecedes(xid, *NewRelfrozenxid)) + *NewRelfrozenxid = xid; + if (TransactionIdPrecedes(xid, cutoff_xid)) + needs_freeze = true; + } } - return false; + return needs_freeze; } /* diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c index 7614d6108..eade44ed0 100644 --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -171,8 +171,10 @@ typedef struct LVRelState /* VACUUM operation's cutoff for freezing XIDs and MultiXactIds */ TransactionId FreezeLimit; MultiXactId MultiXactCutoff; - /* Are FreezeLimit/MultiXactCutoff still valid? */ - bool freeze_cutoffs_valid; + + /* Track new pg_class.relfrozenxid/pg_class.relminmxid values */ + TransactionId NewRelfrozenxid; + MultiXactId NewRelminmxid; /* Error reporting state */ char *relnamespace; @@ -330,6 +332,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, PgStat_Counter startreadtime = 0; PgStat_Counter startwritetime = 0; TransactionId OldestXmin; + MultiXactId OldestMxact; TransactionId FreezeLimit; MultiXactId MultiXactCutoff; @@ -366,8 +369,8 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, params->freeze_table_age, params->multixact_freeze_min_age, params->multixact_freeze_table_age, - &OldestXmin, &FreezeLimit, - &MultiXactCutoff); + &OldestXmin, &OldestMxact, + &FreezeLimit, &MultiXactCutoff); skipwithvm = true; if (params->options & VACOPT_DISABLE_PAGE_SKIPPING) @@ -432,8 +435,10 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, vacrel->OldestXmin = OldestXmin; vacrel->FreezeLimit = FreezeLimit; vacrel->MultiXactCutoff = MultiXactCutoff; - /* Track if cutoffs became invalid (possible in !aggressive case only) */ - vacrel->freeze_cutoffs_valid = true; + + /* Initialize values used to advance relfrozenxid/relminmxid at the end */ + vacrel->NewRelfrozenxid = OldestXmin; + vacrel->NewRelminmxid = OldestMxact; vacrel->relnamespace = get_namespace_name(RelationGetNamespace(rel)); vacrel->relname = pstrdup(RelationGetRelationName(rel)); @@ -522,16 +527,18 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, * Aggressive VACUUM must reliably advance relfrozenxid (and relminmxid). * We are able to advance relfrozenxid in a non-aggressive VACUUM too, * provided we didn't skip any all-visible (not all-frozen) pages using - * the visibility map, and assuming that we didn't fail to get a cleanup - * lock that made it unsafe with respect to FreezeLimit (or perhaps our - * MultiXactCutoff) established for VACUUM operation. + * the visibility map. A non-aggressive VACUUM might only be able to + * advance relfrozenxid to an XID from before FreezeLimit (or a relminmxid + * from before MultiXactCutoff) when it wasn't possible to freeze some + * tuples due to our inability to acquire a cleanup lock, but the effect + * is usually insignificant -- NewRelfrozenxid value still has a decent + * chance of being much more recent that the existing relfrozenxid. * * NB: We must use orig_rel_pages, not vacrel->rel_pages, since we want * the rel_pages used by lazy_scan_heap, which won't match when we * happened to truncate the relation afterwards. */ - if (vacrel->scanned_pages + vacrel->frozenskipped_pages < orig_rel_pages || - !vacrel->freeze_cutoffs_valid) + if (vacrel->scanned_pages + vacrel->frozenskipped_pages < orig_rel_pages) { /* Cannot advance relfrozenxid/relminmxid -- just update pg_class */ Assert(!aggressive); @@ -548,7 +555,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, orig_rel_pages); vac_update_relstats(rel, new_rel_pages, new_live_tuples, new_rel_allvisible, vacrel->nindexes > 0, - FreezeLimit, MultiXactCutoff, + vacrel->NewRelfrozenxid, vacrel->NewRelminmxid, &frozenxid_updated, &minmulti_updated, false); } @@ -650,17 +657,17 @@ heap_vacuum_rel(Relation rel, VacuumParams *params, OldestXmin, diff); if (frozenxid_updated) { - diff = (int32) (FreezeLimit - vacrel->relfrozenxid); + diff = (int32) (vacrel->NewRelfrozenxid - vacrel->relfrozenxid); appendStringInfo(&buf, _("new relfrozenxid: %u, which is %d xids ahead of previous value\n"), - FreezeLimit, diff); + vacrel->NewRelfrozenxid, diff); } if (minmulti_updated) { - diff = (int32) (MultiXactCutoff - vacrel->relminmxid); + diff = (int32) (vacrel->NewRelminmxid - vacrel->relminmxid); appendStringInfo(&buf, _("new relminmxid: %u, which is %d mxids ahead of previous value\n"), - MultiXactCutoff, diff); + vacrel->NewRelminmxid, diff); } if (orig_rel_pages > 0) { @@ -1628,6 +1635,8 @@ lazy_scan_prune(LVRelState *vacrel, int nfrozen; OffsetNumber deadoffsets[MaxHeapTuplesPerPage]; xl_heap_freeze_tuple frozen[MaxHeapTuplesPerPage]; + TransactionId NewRelfrozenxid; + MultiXactId NewRelminmxid; Assert(BufferGetBlockNumber(buf) == blkno); @@ -1636,6 +1645,8 @@ lazy_scan_prune(LVRelState *vacrel, retry: /* Initialize (or reset) page-level counters */ + NewRelfrozenxid = vacrel->NewRelfrozenxid; + NewRelminmxid = vacrel->NewRelminmxid; tuples_deleted = 0; lpdead_items = 0; recently_dead_tuples = 0; @@ -1845,7 +1856,9 @@ retry: vacrel->FreezeLimit, vacrel->MultiXactCutoff, &frozen[nfrozen], - &tuple_totally_frozen)) + &tuple_totally_frozen, + &NewRelfrozenxid, + &NewRelminmxid)) { /* Will execute freeze below */ frozen[nfrozen++].offset = offnum; @@ -1859,13 +1872,16 @@ retry: prunestate->all_frozen = false; } + vacrel->offnum = InvalidOffsetNumber; + /* * We have now divided every item on the page into either an LP_DEAD item * that will need to be vacuumed in indexes later, or a LP_NORMAL tuple * that remains and needs to be considered for freezing now (LP_UNUSED and * LP_REDIRECT items also remain, but are of no further interest to us). */ - vacrel->offnum = InvalidOffsetNumber; + vacrel->NewRelfrozenxid = NewRelfrozenxid; + vacrel->NewRelminmxid = NewRelminmxid; /* * Consider the need to freeze any items with tuple storage from the page @@ -2009,9 +2025,9 @@ retry: * We'll always return true for a non-aggressive VACUUM, even when we know * that this will cause them to miss out on freezing tuples from before * vacrel->FreezeLimit cutoff -- they should never have to wait for a cleanup - * lock. This does mean that they definitely won't be able to advance - * relfrozenxid opportunistically (same applies to vacrel->MultiXactCutoff and - * relminmxid). Caller waits for full cleanup lock when we return false. + * lock. This does mean that they will have NewRelfrozenxid ratcheting back + * to a known-safe value (same applies to NewRelminmxid). Caller waits for + * full cleanup lock when we return false. * * See lazy_scan_prune for an explanation of hastup return flag. The * hasfreespace flag instructs caller on whether or not it should do generic @@ -2035,6 +2051,8 @@ lazy_scan_noprune(LVRelState *vacrel, missed_dead_tuples; HeapTupleHeader tupleheader; OffsetNumber deadoffsets[MaxHeapTuplesPerPage]; + TransactionId NewRelfrozenxid = vacrel->NewRelfrozenxid; + MultiXactId NewRelminmxid = vacrel->NewRelminmxid; Assert(BufferGetBlockNumber(buf) == blkno); @@ -2081,7 +2099,8 @@ lazy_scan_noprune(LVRelState *vacrel, tupleheader = (HeapTupleHeader) PageGetItem(page, itemid); if (heap_tuple_needs_freeze(tupleheader, vacrel->FreezeLimit, - vacrel->MultiXactCutoff, buf)) + vacrel->MultiXactCutoff, + &NewRelfrozenxid, &NewRelminmxid, buf)) { if (vacrel->aggressive) { @@ -2091,10 +2110,11 @@ lazy_scan_noprune(LVRelState *vacrel, } /* - * Current non-aggressive VACUUM operation definitely won't be - * able to advance relfrozenxid or relminmxid + * A non-aggressive VACUUM doesn't have to wait on a cleanup lock + * to ensure that it advances relfrozenxid to a sufficiently + * recent XID that happens to be present on this page. It can + * just accept an older New/final relfrozenxid instead. */ - vacrel->freeze_cutoffs_valid = false; } num_tuples++; @@ -2144,6 +2164,14 @@ lazy_scan_noprune(LVRelState *vacrel, vacrel->offnum = InvalidOffsetNumber; + /* + * We have committed to not freezing the tuples on this page (always + * happens with a non-aggressive VACUUM), so make sure that the target + * relfrozenxid/relminmxid values reflect the XIDs/MXIDs we encountered + */ + vacrel->NewRelfrozenxid = NewRelfrozenxid; + vacrel->NewRelminmxid = NewRelminmxid; + /* * Now save details of the LP_DEAD items from the page in vacrel (though * only when VACUUM uses two-pass strategy). diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 66b87347d..6bd6688ae 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -767,6 +767,7 @@ copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose, TupleDesc oldTupDesc PG_USED_FOR_ASSERTS_ONLY; TupleDesc newTupDesc PG_USED_FOR_ASSERTS_ONLY; TransactionId OldestXmin; + MultiXactId oldestMxact; TransactionId FreezeXid; MultiXactId MultiXactCutoff; bool use_sort; @@ -856,8 +857,8 @@ copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose, * Since we're going to rewrite the whole table anyway, there's no reason * not to be aggressive about this. */ - vacuum_set_xid_limits(OldHeap, 0, 0, 0, 0, - &OldestXmin, &FreezeXid, &MultiXactCutoff); + vacuum_set_xid_limits(OldHeap, 0, 0, 0, 0, &OldestXmin, &oldestMxact, + &FreezeXid, &MultiXactCutoff); /* * FreezeXid will become the table's new relfrozenxid, and that mustn't go diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index ddf6279c7..c39e8088a 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -950,10 +950,28 @@ get_all_vacuum_rels(int options) * The output parameters are: * - oldestXmin is the Xid below which tuples deleted by any xact (that * committed) should be considered DEAD, not just RECENTLY_DEAD. - * - freezeLimit is the Xid below which all Xids are replaced by - * FrozenTransactionId during vacuum. + * - oldestMxact is the Mxid below which MultiXacts are definitely not + * seen as visible by any running transaction. + * - freezeLimit is the Xid below which all Xids are definitely replaced by + * FrozenTransactionId during aggressive vacuums. * - multiXactCutoff is the value below which all MultiXactIds are removed * from Xmax. + * + * oldestXmin and oldestMxact can be thought of as the most recent values that + * can ever be passed to vac_update_relstats() as frozenxid and minmulti + * arguments. These exact values will be used when no newer XIDs or + * MultiXacts remain in the heap relation (e.g., with an empty table). It's + * typical for vacuumlazy.c caller to notice that older XIDs/Multixacts remain + * in the table, which will force it to use older value. These older final + * values may not be any newer than the preexisting frozenxid/minmulti values + * from pg_class in extreme cases. The final values are frequently fairly + * close to the optimal values that we give to vacuumlazy.c, though. + * + * An aggressive VACUUM always provides vac_update_relstats() arguments that + * are >= freezeLimit and >= multiXactCutoff. A non-aggressive VACUUM may + * provide arguments that are either newer or older than freezeLimit and + * multiXactCutoff, or non-valid values (indicating that pg_class level + * cutoffs cannot be advanced at all). */ bool vacuum_set_xid_limits(Relation rel, @@ -962,6 +980,7 @@ vacuum_set_xid_limits(Relation rel, int multixact_freeze_min_age, int multixact_freeze_table_age, TransactionId *oldestXmin, + MultiXactId *oldestMxact, TransactionId *freezeLimit, MultiXactId *multiXactCutoff) { @@ -970,7 +989,6 @@ vacuum_set_xid_limits(Relation rel, int effective_multixact_freeze_max_age; TransactionId limit; TransactionId safeLimit; - MultiXactId oldestMxact; MultiXactId mxactLimit; MultiXactId safeMxactLimit; int freezetable; @@ -1066,9 +1084,11 @@ vacuum_set_xid_limits(Relation rel, effective_multixact_freeze_max_age / 2); Assert(mxid_freezemin >= 0); + /* Remember for caller */ + *oldestMxact = GetOldestMultiXactId(); + /* compute the cutoff multi, being careful to generate a valid value */ - oldestMxact = GetOldestMultiXactId(); - mxactLimit = oldestMxact - mxid_freezemin; + mxactLimit = *oldestMxact - mxid_freezemin; if (mxactLimit < FirstMultiXactId) mxactLimit = FirstMultiXactId; @@ -1083,8 +1103,8 @@ vacuum_set_xid_limits(Relation rel, (errmsg("oldest multixact is far in the past"), errhint("Close open transactions with multixacts soon to avoid wraparound problems."))); /* Use the safe limit, unless an older mxact is still running */ - if (MultiXactIdPrecedes(oldestMxact, safeMxactLimit)) - mxactLimit = oldestMxact; + if (MultiXactIdPrecedes(*oldestMxact, safeMxactLimit)) + mxactLimit = *oldestMxact; else mxactLimit = safeMxactLimit; } -- 2.30.2