From 684a745f55057edd2365a7125ebcb7a54a4db8f8 Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Thu, 2 Oct 2025 11:07:30 +0900 Subject: [PATCH] pgstattuple: Improve reports generated for indexes (hash, gist, btree) pgstattuple checks the state of the pages retrieved for gist and hash using some check functions from each index AM, respectively gistcheckpage() and _hash_checkpage(). When these are called, they would fail when bumping on data that is found as incorrect (like opaque area size not matching, or empty pages), contrary to btree that simply discards these cases and continues to aggregate data. Zero pages can happen after a crash, with these AMs being able to do an internal cleanup when these are seen. Also, sporadic failures are annoying when doing for example a large-scale diagnostic query based on pgstattuple with a join of pg_class, as it forces one to use tricks like quals to discard hash or gist indexes, or use a PL wrapper able to catch errors. This commit changes the reports generated for btree, gist and hash to be more user-friendly; - When seeing an empty page, report it as free space. This new rule applies to gist and hash, and already applied to btree. - For btree, a check based on the size of BTPageOpaqueData is added. - For gist indexes, gistcheckpage() is not called anymore, replaced by a check based on the size of GISTPageOpaqueData. - For hash indexes, instead of _hash_getbuf_with_strategy(), use a direct call to ReadBufferExtended(), coupled with a check based on HashPageOpaqueData. The opaque area size check was already used. - Pages that do not match these criterias are discarded from the stats reports generated. There have been a couple of bug reports over the years that complained about the current behavior for hash and gist, as being not that useful, with nothing being done about it. Hence this change is backpatched down to v13. Reported-by: Noah Misch Author: Nitin Motiani Reviewed-by: Dilip Kumar Discussion: https://postgr.es/m/CAH5HC95gT1J3dRYK4qEnaywG8RqjbwDdt04wuj8p39R=HukayA@mail.gmail.com Backpatch-through: 13 --- contrib/pgstattuple/pgstattuple.c | 32 +++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/contrib/pgstattuple/pgstattuple.c b/contrib/pgstattuple/pgstattuple.c index b5de68b7232..6a7f8cb4a7c 100644 --- a/contrib/pgstattuple/pgstattuple.c +++ b/contrib/pgstattuple/pgstattuple.c @@ -424,7 +424,7 @@ pgstat_btree_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno, /* fully empty page */ stat->free_space += BLCKSZ; } - else + else if (PageGetSpecialSize(page) == MAXALIGN(sizeof(BTPageOpaqueData))) { BTPageOpaque opaque; @@ -458,10 +458,16 @@ pgstat_hash_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno, Buffer buf; Page page; - buf = _hash_getbuf_with_strategy(rel, blkno, HASH_READ, 0, bstrategy); + buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy); + LockBuffer(buf, HASH_READ); page = BufferGetPage(buf); - if (PageGetSpecialSize(page) == MAXALIGN(sizeof(HashPageOpaqueData))) + if (PageIsNew(page)) + { + /* fully empty page */ + stat->free_space += BLCKSZ; + } + else if (PageGetSpecialSize(page) == MAXALIGN(sizeof(HashPageOpaqueData))) { HashPageOpaque opaque; @@ -502,17 +508,23 @@ pgstat_gist_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno, buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy); LockBuffer(buf, GIST_SHARE); - gistcheckpage(rel, buf); page = BufferGetPage(buf); - - if (GistPageIsLeaf(page)) + if (PageIsNew(page)) { - pgstat_index_page(stat, page, FirstOffsetNumber, - PageGetMaxOffsetNumber(page)); + /* fully empty page */ + stat->free_space += BLCKSZ; } - else + else if (PageGetSpecialSize(page) == MAXALIGN(sizeof(GISTPageOpaqueData))) { - /* root or node */ + if (GistPageIsLeaf(page)) + { + pgstat_index_page(stat, page, FirstOffsetNumber, + PageGetMaxOffsetNumber(page)); + } + else + { + /* root or node */ + } } UnlockReleaseBuffer(buf); -- 2.39.5