📄 nbtxlog.c
字号:
/*------------------------------------------------------------------------- * * nbtxlog.c * WAL replay logic for btrees. * * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION * $PostgreSQL: pgsql/src/backend/access/nbtree/nbtxlog.c,v 1.24.2.1 2006/03/28 21:17:31 tgl Exp $ * *------------------------------------------------------------------------- */#include "postgres.h"#include "access/nbtree.h"#include "access/xlogutils.h"/* * We must keep track of expected insertions due to page splits, and apply * them manually if they are not seen in the WAL log during replay. This * makes it safe for page insertion to be a multiple-WAL-action process. * * The data structure is a simple linked list --- this should be good enough, * since we don't expect a page split to remain incomplete for long. */typedef struct bt_incomplete_split{ RelFileNode node; /* the index */ BlockNumber leftblk; /* left half of split */ BlockNumber rightblk; /* right half of split */ bool is_root; /* we split the root */} bt_incomplete_split;static List *incomplete_splits;static voidlog_incomplete_split(RelFileNode node, BlockNumber leftblk, BlockNumber rightblk, bool is_root){ bt_incomplete_split *split = palloc(sizeof(bt_incomplete_split)); split->node = node; split->leftblk = leftblk; split->rightblk = rightblk; split->is_root = is_root; incomplete_splits = lappend(incomplete_splits, split);}static voidforget_matching_split(Relation reln, RelFileNode node, BlockNumber insertblk, OffsetNumber offnum, bool is_root){ Buffer buffer; Page page; BTItem btitem; BlockNumber rightblk; ListCell *l; /* Get downlink TID from page */ buffer = XLogReadBuffer(false, reln, insertblk); if (!BufferIsValid(buffer)) elog(PANIC, "forget_matching_split: block unfound"); page = (Page) BufferGetPage(buffer); btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum)); rightblk = ItemPointerGetBlockNumber(&(btitem->bti_itup.t_tid)); Assert(ItemPointerGetOffsetNumber(&(btitem->bti_itup.t_tid)) == P_HIKEY); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); ReleaseBuffer(buffer); foreach(l, incomplete_splits) { bt_incomplete_split *split = (bt_incomplete_split *) lfirst(l); if (RelFileNodeEquals(node, split->node) && rightblk == split->rightblk) { if (is_root != split->is_root) elog(LOG, "forget_matching_split: fishy is_root data"); incomplete_splits = list_delete_ptr(incomplete_splits, split); break; /* need not look further */ } }}static void_bt_restore_page(Page page, char *from, int len){ BTItemData btdata; Size itemsz; char *end = from + len; for (; from < end;) { memcpy(&btdata, from, sizeof(BTItemData)); itemsz = IndexTupleDSize(btdata.bti_itup) + (sizeof(BTItemData) - sizeof(IndexTupleData)); itemsz = MAXALIGN(itemsz); if (PageAddItem(page, (Item) from, itemsz, FirstOffsetNumber, LP_USED) == InvalidOffsetNumber) elog(PANIC, "_bt_restore_page: can't add item to page"); from += itemsz; }}static void_bt_restore_meta(Relation reln, XLogRecPtr lsn, BlockNumber root, uint32 level, BlockNumber fastroot, uint32 fastlevel){ Buffer metabuf; Page metapg; BTMetaPageData *md; BTPageOpaque pageop; metabuf = XLogReadBuffer(true, reln, BTREE_METAPAGE); if (!BufferIsValid(metabuf)) elog(PANIC, "_bt_restore_meta: no metapage"); metapg = BufferGetPage(metabuf); _bt_pageinit(metapg, BufferGetPageSize(metabuf)); md = BTPageGetMeta(metapg); md->btm_magic = BTREE_MAGIC; md->btm_version = BTREE_VERSION; md->btm_root = root; md->btm_level = level; md->btm_fastroot = fastroot; md->btm_fastlevel = fastlevel; pageop = (BTPageOpaque) PageGetSpecialPointer(metapg); pageop->btpo_flags = BTP_META; /* * Set pd_lower just past the end of the metadata. This is not essential * but it makes the page look compressible to xlog.c. */ ((PageHeader) metapg)->pd_lower = ((char *) md + sizeof(BTMetaPageData)) - (char *) metapg; PageSetLSN(metapg, lsn); PageSetTLI(metapg, ThisTimeLineID); LockBuffer(metabuf, BUFFER_LOCK_UNLOCK); WriteBuffer(metabuf);}static voidbtree_xlog_insert(bool isleaf, bool ismeta, XLogRecPtr lsn, XLogRecord *record){ xl_btree_insert *xlrec = (xl_btree_insert *) XLogRecGetData(record); Relation reln; Buffer buffer; Page page; char *datapos; int datalen; xl_btree_metadata md; datapos = (char *) xlrec + SizeOfBtreeInsert; datalen = record->xl_len - SizeOfBtreeInsert; if (ismeta) { memcpy(&md, datapos, sizeof(xl_btree_metadata)); datapos += sizeof(xl_btree_metadata); datalen -= sizeof(xl_btree_metadata); } if ((record->xl_info & XLR_BKP_BLOCK_1) && !ismeta && incomplete_splits == NIL) return; /* nothing to do */ reln = XLogOpenRelation(xlrec->target.node); if (!RelationIsValid(reln)) return; if (!(record->xl_info & XLR_BKP_BLOCK_1)) { buffer = XLogReadBuffer(false, reln, ItemPointerGetBlockNumber(&(xlrec->target.tid))); if (!BufferIsValid(buffer)) elog(PANIC, "btree_insert_redo: block unfound"); page = (Page) BufferGetPage(buffer); if (PageIsNew((PageHeader) page)) elog(PANIC, "btree_insert_redo: uninitialized page"); if (XLByteLE(lsn, PageGetLSN(page))) { LockBuffer(buffer, BUFFER_LOCK_UNLOCK); ReleaseBuffer(buffer); } else { if (PageAddItem(page, (Item) datapos, datalen, ItemPointerGetOffsetNumber(&(xlrec->target.tid)), LP_USED) == InvalidOffsetNumber) elog(PANIC, "btree_insert_redo: failed to add item"); PageSetLSN(page, lsn); PageSetTLI(page, ThisTimeLineID); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); WriteBuffer(buffer); } } if (ismeta) _bt_restore_meta(reln, lsn, md.root, md.level, md.fastroot, md.fastlevel); /* Forget any split this insertion completes */ if (!isleaf && incomplete_splits != NIL) { forget_matching_split(reln, xlrec->target.node, ItemPointerGetBlockNumber(&(xlrec->target.tid)), ItemPointerGetOffsetNumber(&(xlrec->target.tid)), false); }}static voidbtree_xlog_split(bool onleft, bool isroot, XLogRecPtr lsn, XLogRecord *record){ xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record); Relation reln; BlockNumber targetblk; BlockNumber leftsib; BlockNumber rightsib; Buffer buffer; Page page; BTPageOpaque pageop; reln = XLogOpenRelation(xlrec->target.node); if (!RelationIsValid(reln)) return; targetblk = ItemPointerGetBlockNumber(&(xlrec->target.tid)); leftsib = (onleft) ? targetblk : xlrec->otherblk; rightsib = (onleft) ? xlrec->otherblk : targetblk; /* Left (original) sibling */ buffer = XLogReadBuffer(true, reln, leftsib); if (!BufferIsValid(buffer)) elog(PANIC, "btree_split_redo: lost left sibling"); page = (Page) BufferGetPage(buffer); _bt_pageinit(page, BufferGetPageSize(buffer)); pageop = (BTPageOpaque) PageGetSpecialPointer(page); pageop->btpo_prev = xlrec->leftblk; pageop->btpo_next = rightsib; pageop->btpo.level = xlrec->level; pageop->btpo_flags = (xlrec->level == 0) ? BTP_LEAF : 0; _bt_restore_page(page, (char *) xlrec + SizeOfBtreeSplit, xlrec->leftlen); PageSetLSN(page, lsn); PageSetTLI(page, ThisTimeLineID); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); WriteBuffer(buffer); /* Right (new) sibling */ buffer = XLogReadBuffer(true, reln, rightsib); if (!BufferIsValid(buffer)) elog(PANIC, "btree_split_redo: lost right sibling"); page = (Page) BufferGetPage(buffer); _bt_pageinit(page, BufferGetPageSize(buffer)); pageop = (BTPageOpaque) PageGetSpecialPointer(page); pageop->btpo_prev = leftsib; pageop->btpo_next = xlrec->rightblk; pageop->btpo.level = xlrec->level; pageop->btpo_flags = (xlrec->level == 0) ? BTP_LEAF : 0; _bt_restore_page(page, (char *) xlrec + SizeOfBtreeSplit + xlrec->leftlen, record->xl_len - SizeOfBtreeSplit - xlrec->leftlen); PageSetLSN(page, lsn); PageSetTLI(page, ThisTimeLineID); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); WriteBuffer(buffer); /* Fix left-link of right (next) page */ if (!(record->xl_info & XLR_BKP_BLOCK_1)) { if (xlrec->rightblk != P_NONE) { buffer = XLogReadBuffer(false, reln, xlrec->rightblk); if (!BufferIsValid(buffer)) elog(PANIC, "btree_split_redo: lost next right page"); page = (Page) BufferGetPage(buffer); if (PageIsNew((PageHeader) page)) elog(PANIC, "btree_split_redo: uninitialized next right page"); if (XLByteLE(lsn, PageGetLSN(page))) { LockBuffer(buffer, BUFFER_LOCK_UNLOCK); ReleaseBuffer(buffer); } else { pageop = (BTPageOpaque) PageGetSpecialPointer(page); pageop->btpo_prev = rightsib; PageSetLSN(page, lsn); PageSetTLI(page, ThisTimeLineID); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); WriteBuffer(buffer); } } } /* Forget any split this insertion completes */ if (xlrec->level > 0 && incomplete_splits != NIL) { forget_matching_split(reln, xlrec->target.node, ItemPointerGetBlockNumber(&(xlrec->target.tid)), ItemPointerGetOffsetNumber(&(xlrec->target.tid)), false); } /* The job ain't done till the parent link is inserted... */ log_incomplete_split(xlrec->target.node, leftsib, rightsib, isroot);}static voidbtree_xlog_delete(XLogRecPtr lsn, XLogRecord *record){ xl_btree_delete *xlrec; Relation reln; Buffer buffer; Page page; if (record->xl_info & XLR_BKP_BLOCK_1) return; xlrec = (xl_btree_delete *) XLogRecGetData(record); reln = XLogOpenRelation(xlrec->node); if (!RelationIsValid(reln)) return; buffer = XLogReadBuffer(false, reln, xlrec->block); if (!BufferIsValid(buffer)) elog(PANIC, "btree_delete_redo: block unfound"); page = (Page) BufferGetPage(buffer); if (PageIsNew((PageHeader) page)) elog(PANIC, "btree_delete_redo: uninitialized page"); if (XLByteLE(lsn, PageGetLSN(page))) { LockBuffer(buffer, BUFFER_LOCK_UNLOCK); ReleaseBuffer(buffer); return; } if (record->xl_len > SizeOfBtreeDelete) { OffsetNumber *unused; OffsetNumber *unend; unused = (OffsetNumber *) ((char *) xlrec + SizeOfBtreeDelete); unend = (OffsetNumber *) ((char *) xlrec + record->xl_len); PageIndexMultiDelete(page, unused, unend - unused); } PageSetLSN(page, lsn); PageSetTLI(page, ThisTimeLineID); LockBuffer(buffer, BUFFER_LOCK_UNLOCK); WriteBuffer(buffer);}static voidbtree_xlog_delete_page(bool ismeta, XLogRecPtr lsn, XLogRecord *record){ xl_btree_delete_page *xlrec = (xl_btree_delete_page *) XLogRecGetData(record); Relation reln; BlockNumber parent; BlockNumber target; BlockNumber leftsib; BlockNumber rightsib; Buffer buffer; Page page; BTPageOpaque pageop; reln = XLogOpenRelation(xlrec->target.node); if (!RelationIsValid(reln)) return; parent = ItemPointerGetBlockNumber(&(xlrec->target.tid)); target = xlrec->deadblk; leftsib = xlrec->leftblk; rightsib = xlrec->rightblk; /* parent page */ if (!(record->xl_info & XLR_BKP_BLOCK_1)) { buffer = XLogReadBuffer(false, reln, parent); if (!BufferIsValid(buffer)) elog(PANIC, "btree_delete_page_redo: parent block unfound"); page = (Page) BufferGetPage(buffer); pageop = (BTPageOpaque) PageGetSpecialPointer(page);
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -