From 1667148a4dd98cea28b8b53d57dbc1eece1b0b5c Mon Sep 17 00:00:00 2001 From: Andres Freund Date: Tue, 1 May 2018 13:30:12 -0700 Subject: [PATCH] Improve representation of 'moved partitions' indicator on deleted tuples. Previously a tuple that has been moved to a different partition (see f16241bef7c), set the block number on the old tuple to an invalid value to indicate that fact. But the tuple offset was left untouched. That turned out to trigger a wal_consistency_checking failure as reported by Peter Geoghegan, as the offset wasn't always overwritten during WAL replay. Heikki observed that we're wasting valuable data by not putting information also in the offset. Thus set that to MovedPartitionsOffsetNumber when a tuple indicates it has moved. We continue to set the block number to MovedPartitionsBlockNumber, as that seems more likely to cause problems for code not updated to know about moved tuples. As t_ctid's offset number is now always set, this refinement also fixes the wal_consistency_checking issue. This technically is a minor disk format break, with previously created moved tuples not being recognized anymore. But since there not even has been a beta release since f16241bef7c... Reported-By: Peter Geoghegan Author: Heikki Linnakangas, Amul Sul Discussion: https://postgr.es/m/CAH2-Wzm9ty+1BX7-GMNJ=xPRg67oJTVeDNdA9LSyJJtMgRiCMA@mail.gmail.com --- src/include/access/htup_details.h | 29 ++++++++++++----------------- src/include/storage/itemptr.h | 29 +++++++++++++++++++++++++++-- 2 files changed, 39 insertions(+), 19 deletions(-) diff --git a/src/include/access/htup_details.h b/src/include/access/htup_details.h index cf56d4ace4..1867a70f6f 100644 --- a/src/include/access/htup_details.h +++ b/src/include/access/htup_details.h @@ -83,13 +83,15 @@ * * A word about t_ctid: whenever a new tuple is stored on disk, its t_ctid * is initialized with its own TID (location). If the tuple is ever updated, - * its t_ctid is changed to point to the replacement version of the tuple or - * the block number (ip_blkid) is invalidated if the tuple is moved from one - * partition to another partition relation due to an update of the partition - * key. Thus, a tuple is the latest version of its row iff XMAX is invalid or + * its t_ctid is changed to point to the replacement version of the tuple. Or + * if the tuple is moved from one partition to another, due to an update of + * the partition key, t_ctid is set to a special value to indicate that + * (see ItemPointerSetMovedPartitions). Thus, a tuple is the latest version + * of its row iff XMAX is invalid or * t_ctid points to itself (in which case, if XMAX is valid, the tuple is * either locked or deleted). One can follow the chain of t_ctid links - * to find the newest version of the row. Beware however that VACUUM might + * to find the newest version of the row, unless it was moved to a different + * partition. Beware however that VACUUM might * erase the pointed-to (newer) tuple before erasing the pointing (older) * tuple. Hence, when following a t_ctid link, it is necessary to check * to see if the referenced slot is empty or contains an unrelated tuple. @@ -287,14 +289,6 @@ struct HeapTupleHeaderData */ #define HEAP_TUPLE_HAS_MATCH HEAP_ONLY_TUPLE /* tuple has a join match */ -/* - * Special value used in t_ctid.ip_posid, to indicate that it holds a - * speculative insertion token rather than a real TID. This must be higher - * than MaxOffsetNumber, so that it can be distinguished from a valid - * offset number in a regular item pointer. - */ -#define SpecTokenOffsetNumber 0xfffe - /* * HeapTupleHeader accessor macros * @@ -447,11 +441,12 @@ do { \ ItemPointerSet(&(tup)->t_ctid, token, SpecTokenOffsetNumber) \ ) -#define HeapTupleHeaderSetMovedPartitions(tup) \ - ItemPointerSetMovedPartitions(&(tup)->t_ctid) - #define HeapTupleHeaderIndicatesMovedPartitions(tup) \ - ItemPointerIndicatesMovedPartitions(&tup->t_ctid) + (ItemPointerGetOffsetNumber(&(tup)->t_ctid) == MovedPartitionsOffsetNumber && \ + ItemPointerGetBlockNumberNoCheck(&(tup)->t_ctid) == MovedPartitionsBlockNumber) + +#define HeapTupleHeaderSetMovedPartitions(tup) \ + ItemPointerSet(&(tup)->t_ctid, MovedPartitionsBlockNumber, MovedPartitionsOffsetNumber) #define HeapTupleHeaderGetDatumLength(tup) \ VARSIZE(tup) diff --git a/src/include/storage/itemptr.h b/src/include/storage/itemptr.h index 626c98f969..d87101f270 100644 --- a/src/include/storage/itemptr.h +++ b/src/include/storage/itemptr.h @@ -48,6 +48,28 @@ ItemPointerData; typedef ItemPointerData *ItemPointer; +/* ---------------- + * special values used in heap tuples (t_ctid) + * ---------------- + */ + +/* + * If a heap tuple holds a speculative insertion token rather than a real + * TID, ip_posid is set to SpecTokenOffsetNumber, and the token is stored in + * ip_blkid. SpecTokenOffsetNumber must be higher than MaxOffsetNumber, so + * that it can be distinguished from a valid offset number in a regular item + * pointer. + */ +#define SpecTokenOffsetNumber 0xfffe + +/* + * When a tuple is moved to a different partition by UPDATE, the t_ctid of + * the old tuple version is set to this magic value. + */ +#define MovedPartitionsOffsetNumber 0xfffd +#define MovedPartitionsBlockNumber InvalidBlockNumber + + /* ---------------- * support macros * ---------------- @@ -160,7 +182,10 @@ typedef ItemPointerData *ItemPointer; * partition. */ #define ItemPointerIndicatesMovedPartitions(pointer) \ - !BlockNumberIsValid(ItemPointerGetBlockNumberNoCheck(pointer)) +( \ + ItemPointerGetOffsetNumber(pointer) == MovedPartitionsOffsetNumber && \ + ItemPointerGetBlockNumberNoCheck(pointer) == MovedPartitionsBlockNumber \ +) /* * ItemPointerSetMovedPartitions @@ -168,7 +193,7 @@ typedef ItemPointerData *ItemPointer; * different partition. */ #define ItemPointerSetMovedPartitions(pointer) \ - ItemPointerSetBlockNumber((pointer), InvalidBlockNumber) + ItemPointerSet((pointer), MovedPartitionsBlockNumber, MovedPartitionsOffsetNumber) /* ---------------- * externs -- 2.40.0