commit 5b42c832b92b08d6eff394c5608bf62791b704d6 Author: Anastasia Date: Wed Feb 28 17:53:39 2018 +0300 optimial WAL for GIST diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c index 51c32e4..b32a323 100644 --- a/src/backend/access/gist/gist.c +++ b/src/backend/access/gist/gist.c @@ -169,7 +169,7 @@ gistinsert(Relation r, Datum *values, bool *isnull, values, isnull, true /* size is currently bogus */ ); itup->t_tid = *ht_ctid; - gistdoinsert(r, itup, 0, giststate); + gistdoinsert(r, itup, 0, giststate, false); /* cleanup */ MemoryContextSwitchTo(oldCxt); @@ -215,7 +215,8 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, BlockNumber *newblkno, Buffer leftchildbuf, List **splitinfo, - bool markfollowright) + bool markfollowright, + bool is_build) { BlockNumber blkno = BufferGetBlockNumber(buffer); Page page = BufferGetPage(buffer); @@ -451,7 +452,7 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, * insertion for that. NB: The number of pages and data segments * specified here must match the calculations in gistXLogSplit()! */ - if (RelationNeedsWAL(rel)) + if (RelationNeedsWAL(rel) && !is_build) XLogEnsureRecordSpace(npage, 1 + npage * 2); START_CRIT_SECTION(); @@ -472,18 +473,20 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, PageRestoreTempPage(dist->page, BufferGetPage(dist->buffer)); dist->page = BufferGetPage(dist->buffer); - /* Write the WAL record */ - if (RelationNeedsWAL(rel)) + /* + * Write the WAL record. + * Do not write XLog entry if the insertion is caused by + * index build process. + */ + if (RelationNeedsWAL(rel) && !is_build) recptr = gistXLogSplit(is_leaf, - dist, oldrlink, oldnsn, leftchildbuf, - markfollowright); + dist, oldrlink, oldnsn, leftchildbuf, + markfollowright); else recptr = gistGetFakeLSN(rel); for (ptr = dist; ptr; ptr = ptr->next) - { PageSetLSN(ptr->page, recptr); - } /* * Return the new child buffers to the caller. @@ -537,7 +540,8 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, if (BufferIsValid(leftchildbuf)) MarkBufferDirty(leftchildbuf); - if (RelationNeedsWAL(rel)) + + if (RelationNeedsWAL(rel) && !is_build) { OffsetNumber ndeloffs = 0, deloffs[1]; @@ -560,6 +564,7 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, PageSetLSN(page, recptr); } + if (newblkno) *newblkno = blkno; } @@ -576,17 +581,28 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, * the full page image. There's a chicken-and-egg problem: if we updated * the child pages first, we wouldn't know the recptr of the WAL record * we're about to write. + * + * We use fakeLSNs for inserions caused by index build. And when it is + * finished, we write generic_xlog entry for each index page and update + * all LSNs. In order to keep NSNs less then LSNs after this update, we + * set NSN to InvalidXLogRecPtr, which is the smallest possible NSN. */ + if (BufferIsValid(leftchildbuf)) { Page leftpg = BufferGetPage(leftchildbuf); + XLogRecPtr fakerecptr = InvalidXLogRecPtr; - GistPageSetNSN(leftpg, recptr); - GistClearFollowRight(leftpg); + if (!is_build) + GistPageSetNSN(leftpg, recptr); + else + GistPageSetNSN(leftpg, fakerecptr); + GistClearFollowRight(leftpg); PageSetLSN(leftpg, recptr); } + END_CRIT_SECTION(); return is_split; @@ -598,7 +614,8 @@ gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, * so it does not bother releasing palloc'd allocations. */ void -gistdoinsert(Relation r, IndexTuple itup, Size freespace, GISTSTATE *giststate) +gistdoinsert(Relation r, IndexTuple itup, Size freespace, + GISTSTATE *giststate, bool is_build) { ItemId iid; IndexTuple idxtuple; @@ -610,6 +627,7 @@ gistdoinsert(Relation r, IndexTuple itup, Size freespace, GISTSTATE *giststate) memset(&state, 0, sizeof(GISTInsertState)); state.freespace = freespace; state.r = r; + state.is_build = is_build; /* Start from the root */ firststack.blkno = GIST_ROOT_BLKNO; @@ -1220,7 +1238,7 @@ gistinserttuples(GISTInsertState *state, GISTInsertStack *stack, oldoffnum, NULL, leftchild, &splitinfo, - true); + true, state->is_build); /* * Before recursing up in case the page was split, release locks on the diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c index 434f15f..bfc10cd 100644 --- a/src/backend/access/gist/gistbuild.c +++ b/src/backend/access/gist/gistbuild.c @@ -20,6 +20,7 @@ #include "access/gist_private.h" #include "access/gistxlog.h" #include "access/xloginsert.h" +#include "access/generic_xlog.h" #include "catalog/index.h" #include "miscadmin.h" #include "optimizer/cost.h" @@ -178,18 +179,12 @@ gistbuild(Relation heap, Relation index, IndexInfo *indexInfo) MarkBufferDirty(buffer); - if (RelationNeedsWAL(index)) - { - XLogRecPtr recptr; - - XLogBeginInsert(); - XLogRegisterBuffer(0, buffer, REGBUF_WILL_INIT); - - recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX); - PageSetLSN(page, recptr); - } - else - PageSetLSN(page, gistGetFakeLSN(heap)); + /* + * Do not write index pages to WAL unitl index build is finished. + * But we still need increasing LSNs on each page, so use FakeLSN, + * even for relations which eventually need WAL. + */ + PageSetLSN(page, gistGetFakeLSN(heap)); UnlockReleaseBuffer(buffer); @@ -223,6 +218,15 @@ gistbuild(Relation heap, Relation index, IndexInfo *indexInfo) freeGISTstate(buildstate.giststate); /* + * Create generic wal records for all pages of relation, if necessary. + * It seems reasonable not to generate WAL, if we recieved interrupt + * signal. + */ + CHECK_FOR_INTERRUPTS(); + if (RelationNeedsWAL(index)) + generate_xlog_for_rel(index); + + /* * Return statistics */ result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult)); @@ -484,7 +488,7 @@ gistBuildCallback(Relation index, * locked, we call gistdoinsert directly. */ gistdoinsert(index, itup, buildstate->freespace, - buildstate->giststate); + buildstate->giststate, true); } /* Update tuple count and total size. */ @@ -690,7 +694,7 @@ gistbufferinginserttuples(GISTBuildState *buildstate, Buffer buffer, int level, itup, ntup, oldoffnum, &placed_to_blk, InvalidBuffer, &splitinfo, - false); + false, true); /* * If this is a root split, update the root path item kept in memory. This diff --git a/src/backend/access/gist/gistutil.c b/src/backend/access/gist/gistutil.c index 55cccd2..cb86299 100644 --- a/src/backend/access/gist/gistutil.c +++ b/src/backend/access/gist/gistutil.c @@ -975,6 +975,7 @@ gistproperty(Oid index_oid, int attno, * Temporary and unlogged GiST indexes are not WAL-logged, but we need LSNs * to detect concurrent page splits anyway. This function provides a fake * sequence of LSNs for that purpose. + * Persistent relations are also not WAL-logged while we build index. */ XLogRecPtr gistGetFakeLSN(Relation rel) @@ -995,7 +996,6 @@ gistGetFakeLSN(Relation rel) * Unlogged relations are accessible from other backends, and survive * (clean) restarts. GetFakeLSNForUnloggedRel() handles that for us. */ - Assert(rel->rd_rel->relpersistence == RELPERSISTENCE_UNLOGGED); return GetFakeLSNForUnloggedRel(); } } diff --git a/src/include/access/gist_private.h b/src/include/access/gist_private.h index 36ed724..0588fc7 100644 --- a/src/include/access/gist_private.h +++ b/src/include/access/gist_private.h @@ -241,6 +241,7 @@ typedef struct { Relation r; Size freespace; /* free space to be left */ + bool is_build; GISTInsertStack *stack; } GISTInsertState; @@ -387,9 +388,9 @@ extern MemoryContext createTempGistContext(void); extern GISTSTATE *initGISTstate(Relation index); extern void freeGISTstate(GISTSTATE *giststate); extern void gistdoinsert(Relation r, - IndexTuple itup, - Size freespace, - GISTSTATE *GISTstate); + IndexTuple itup, + Size freespace, + GISTSTATE* giststate, bool is_build); /* A List of these is returned from gistplacetopage() in *splitinfo */ typedef struct @@ -404,7 +405,8 @@ extern bool gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate, OffsetNumber oldoffnum, BlockNumber *newblkno, Buffer leftchildbuf, List **splitinfo, - bool markleftchild); + bool markleftchild, + bool is_build); extern SplitedPageLayout *gistSplit(Relation r, Page page, IndexTuple *itup, int len, GISTSTATE *giststate);