PostgreSQL 14在MVCC上面有所增强，以保证在大批量客户端连接场景下性能不会出现显著下降（详细可参见参考资料中的链接）。本节介绍了提交记录“Don't compute global horizons while building snapshots.”中vacuumlazy.c、indexam.c、nbtpage.c、nbtree.c、nbtxlog.c和spgvacuum.c中的修改以及涉及的相关数据结构。 ### 一、数据结构 N/A ### 二、源码解读 **vacuumlazy.c** ```diff --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -788,6 +788,7 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, /* lazy_scan_heap函数做的事情是清理heap中的每个page，还包括截断死亡元组为死亡行指针，重整page和设置提交状态位， 使用空闲空间构建死亡元组和page链表，计算heap中的存活元组数，如需要则标记pages为全可见状态。 修改： 在调用heap_page_prune清理page时，换成新的heap_page_prune函数，不再依赖OldestXmin */ PROGRESS_VACUUM_MAX_DEAD_TUPLES }; int64 initprog_val[3]; //使用GlobalVisXXX替换OldestXmin + GlobalVisState *vistest; pg_rusage_init(&ru0); @@ -816,6 +817,8 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, vacrelstats->nonempty_pages = 0; vacrelstats->latestRemovedXid = InvalidTransactionId; //使用GlobalVisXXX替换OldestXmin + vistest = GlobalVisTestFor(onerel); + /* * Initialize state for a parallel vacuum. As of now, only one worker can * be used for an index, so we invoke parallelism only if there are at @@ -1239,7 +1242,8 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, * * We count tuples removed by the pruning step as removed by VACUUM. */ //使用新的heap_page_prune函数替换原函数（带OldestXmin参数） - tups_vacuumed += heap_page_prune(onerel, buf, OldestXmin, false, + tups_vacuumed += heap_page_prune(onerel, buf, vistest, false, + InvalidTransactionId, 0, &vacrelstats->latestRemovedXid); /* @@ -1596,14 +1600,16 @@ lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, } /* - * It's possible for the value returned by GetOldestXmin() to move - * backwards, so it's not wrong for us to see tuples that appear to - * not be visible to everyone yet, while PD_ALL_VISIBLE is already - * set. The real safe xmin value never moves backwards, but - * GetOldestXmin() is conservative and sometimes returns a value - * that's unnecessarily small, so if we see that contradiction it just - * means that the tuples that we think are not visible to everyone yet - * actually are, and the PD_ALL_VISIBLE flag is correct. + * It's possible for the value returned by + * GetOldestNonRemovableTransactionId() to move backwards, so it's not + * wrong for us to see tuples that appear to not be visible to + * everyone yet, while PD_ALL_VISIBLE is already set. The real safe + * xmin value never moves backwards, but + * GetOldestNonRemovableTransactionId() is conservative and sometimes + * returns a value that's unnecessarily small, so if we see that + * contradiction it just means that the tuples that we think are not + * visible to everyone yet actually are, and the PD_ALL_VISIBLE flag + * is correct. * * There should never be dead tuples on a page with PD_ALL_VISIBLE * set, however. ``` **indexam.c** ```diff --- a/src/backend/access/index/indexam.c +++ b/src/backend/access/index/indexam.c @@ -519,7 +519,8 @@ index_getnext_tid(IndexScanDesc scan, ScanDirection direction) /* index_getnext_tid : 该函数用于获取下一个TID 修改： 去掉变量RecentGlobalXmin，改为RecentXmin */ SCAN_CHECKS; CHECK_SCAN_PROCEDURE(amgettuple); - Assert(TransactionIdIsValid(RecentGlobalXmin)); + /* XXX: we should assert that a snapshot is pushed or registered */ + Assert(TransactionIdIsValid(RecentXmin)); /* * The AM's amgettuple proc finds the next index entry matching the scan ``` **nbtpage.c** ```diff --- a/src/backend/access/nbtree/nbtpage.c +++ b/src/backend/access/nbtree/nbtpage.c @@ -1097,7 +1097,7 @@ _bt_page_recyclable(Page page) /* _bt_page_recyclable : 用于判断现存的page是否可回收？ */ */ opaque = (BTPageOpaque) PageGetSpecialPointer(page); if (P_ISDELETED(opaque) && //使用GlobalVisXXX函数替换RecentGlobalXmin - TransactionIdPrecedes(opaque->btpo.xact, RecentGlobalXmin)) + GlobalVisCheckRemovableXid(NULL, opaque->btpo.xact)) return true; return false; } @@ -2318,7 +2318,7 @@ _bt_unlink_halfdead_page(Relation rel, Buffer leafbuf, BlockNumber scanblkno, * updated links to the target, ReadNewTransactionId() suffices as an * upper bound. Any scan having retained a now-stale link is advertising * in its PGXACT an xmin less than or equal to the value we read here. It - * will continue to do so, holding back RecentGlobalXmin, for the duration + * will continue to do so, holding back the xmin horizon, for the duration * of that scan. */ page = BufferGetPage(buf); ``` **nbtree** ```diff --- a/src/backend/access/nbtree/nbtree.c +++ b/src/backend/access/nbtree/nbtree.c @@ -808,6 +808,12 @@ _bt_vacuum_needs_cleanup(IndexVacuumInfo *info) /* _bt_vacuum_needs_cleanup : 检查索引是否需要清理 */ metapg = BufferGetPage(metabuf); metad = BTPageGetMeta(metapg); + /* + * XXX: If IndexVacuumInfo contained the heap relation, we could be more + * aggressive about vacuuming non catalog relations by passing the table + * to GlobalVisCheckRemovableXid(). + */ + if (metad->btm_version < BTREE_NOVAC_VERSION) { /* @@ -817,13 +823,12 @@ _bt_vacuum_needs_cleanup(IndexVacuumInfo *info) result = true; } else if (TransactionIdIsValid(metad->btm_oldest_btpo_xact) && //使用GlobalVisXXX函数替换RecentGlobalXmin - TransactionIdPrecedes(metad->btm_oldest_btpo_xact, - RecentGlobalXmin)) + GlobalVisCheckRemovableXid(NULL, metad->btm_oldest_btpo_xact)) { /* * If any oldest btpo.xact from a previously deleted page in the index - * is older than RecentGlobalXmin, then at least one deleted page can - * be recycled -- don't skip cleanup. + * is visible to everyone, then at least one deleted page can be + * recycled -- don't skip cleanup. */ result = true; } @@ -1276,14 +1281,13 @@ backtrack: * own conflict now.) * * Backends with snapshots acquired after a VACUUM starts but - * before it finishes could have a RecentGlobalXmin with a - * later xid than the VACUUM's OldestXmin cutoff. These - * backends might happen to opportunistically mark some index - * tuples LP_DEAD before we reach them, even though they may - * be after our cutoff. We don't try to kill these "extra" - * index tuples in _bt_delitems_vacuum(). This keep things - * simple, and allows us to always avoid generating our own - * conflicts. + * before it finishes could have visibility cutoff with a + * later xid than VACUUM's OldestXmin cutoff. These backends + * might happen to opportunistically mark some index tuples + * LP_DEAD before we reach them, even though they may be after + * our cutoff. We don't try to kill these "extra" index + * tuples in _bt_delitems_vacuum(). This keep things simple, + * and allows us to always avoid generating our own conflicts. */ Assert(!BTreeTupleIsPivot(itup)); if (!BTreeTupleIsPosting(itup)) ``` **nbtxlog.c** ```diff --- a/src/backend/access/nbtree/nbtxlog.c +++ b/src/backend/access/nbtree/nbtxlog.c @@ -948,11 +948,11 @@ btree_xlog_reuse_page(XLogReaderState *record) /* 这里只是简单的改了注释而已 */ * Btree reuse_page records exist to provide a conflict point when we * reuse pages in the index via the FSM. That's all they do though. * - * latestRemovedXid was the page's btpo.xact. The btpo.xact < - * RecentGlobalXmin test in _bt_page_recyclable() conceptually mirrors the - * pgxact->xmin > limitXmin test in GetConflictingVirtualXIDs(). - * Consequently, one XID value achieves the same exclusion effect on - * primary and standby. + * latestRemovedXid was the page's btpo.xact. The + * GlobalVisCheckRemovableXid test in _bt_page_recyclable() conceptually + * mirrors the pgxact->xmin > limitXmin test in + * GetConflictingVirtualXIDs(). Consequently, one XID value achieves the + * same exclusion effect on primary and standby. */ if (InHotStandby) { ``` **spgvacuum.c** ```diff --- a/src/backend/access/spgist/spgvacuum.c +++ b/src/backend/access/spgist/spgvacuum.c @@ -501,10 +501,14 @@ vacuumRedirectAndPlaceholder(Relation index, Buffer buffer) /* vacuumRedirectAndPlaceholder ： 清理给定page中的redirect和placeholder元组 修改： 同样的，使用GlobalVisXXX函数代替RecentGlobalXmin */ OffsetNumber itemToPlaceholder[MaxIndexTuplesPerPage]; OffsetNumber itemnos[MaxIndexTuplesPerPage]; spgxlogVacuumRedirect xlrec; + GlobalVisState *vistest; xlrec.nToPlaceholder = 0; xlrec.newestRedirectXid = InvalidTransactionId; + /* XXX: providing heap relation would allow more pruning */ + vistest = GlobalVisTestFor(NULL); + START_CRIT_SECTION(); /* @@ -521,7 +525,7 @@ vacuumRedirectAndPlaceholder(Relation index, Buffer buffer) dt = (SpGistDeadTuple) PageGetItem(page, PageGetItemId(page, i)); if (dt->tupstate == SPGIST_REDIRECT && - TransactionIdPrecedes(dt->xid, RecentGlobalXmin)) + GlobalVisTestIsRemovableXid(vistest, dt->xid)) { dt->tupstate = SPGIST_PLACEHOLDER; Assert(opaque->nRedirection > 0); ``` ### 三、跟踪分析 N/A ### 四、参考资料 1.[Improving connection scalability: GetSnapshotData()](https://www.postgresql.org/message-id/20200301083601.ews6hz5dduc3w2se%40alap3.anarazel.de) 2.[snapshot scalability: Don't compute global horizons while building snapshots.](https://git.postgresql.org/gitweb/?p=postgresql.git;a=commitdiff;h=dc7420c2c9274a283779ec19718d2d16323640c0)