agora inbox for [email protected]
help / color / mirror / Atom feed[PATCH v7 2/3] Key PGSTAT_KIND_RELATION by relfile locator
82+ messages / 2 participants
[nested] [flat]
* [PATCH v7 2/3] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)
This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:
- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.
That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.
The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.
Please note that:
- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.
- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.
- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
src/backend/access/heap/vacuumlazy.c | 3 +-
src/backend/postmaster/autovacuum.c | 9 +-
src/backend/utils/activity/pgstat_relation.c | 234 +++++++++++++++----
src/backend/utils/adt/pgstatfuncs.c | 22 +-
src/include/pgstat.h | 18 +-
src/include/utils/pgstat_internal.h | 1 +
src/test/recovery/t/029_stats_restart.pl | 40 ++--
7 files changed, 249 insertions(+), 78 deletions(-)
3.3% src/backend/postmaster/
64.6% src/backend/utils/activity/
5.3% src/backend/utils/adt/
7.0% src/include/
18.7% src/test/recovery/t/
diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 61fe623cc60..073f1ff3fe4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -947,8 +947,7 @@ heap_vacuum_rel(Relation rel, const VacuumParams params,
* soon in cases where the failsafe prevented significant amounts of heap
* vacuuming.
*/
- pgstat_report_vacuum(RelationGetRelid(rel),
- rel->rd_rel->relisshared,
+ pgstat_report_vacuum(rel->rd_locator,
Max(vacrel->new_live_tuples, 0),
vacrel->recently_dead_tuples +
vacrel->missed_dead_tuples,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index ed19c74bb19..662495c72fc 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2048,8 +2048,7 @@ do_autovacuum(void)
/* Fetch reloptions and the pgstat entry for this table */
relopts = extract_autovac_opts(tuple, pg_class_desc);
- tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
- relid);
+ tabentry = pgstat_fetch_stat_tabentry_ext(relid);
/* Check if it needs vacuum or analyze */
relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2141,8 +2140,7 @@ do_autovacuum(void)
}
/* Fetch the pgstat entry for this table */
- tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
- relid);
+ tabentry = pgstat_fetch_stat_tabentry_ext(relid);
relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
effective_multixact_freeze_max_age,
@@ -2939,8 +2937,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
PgStat_StatTabEntry *tabentry;
/* fetch the pgstat table entry */
- tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
- relid);
+ tabentry = pgstat_fetch_stat_tabentry_ext(relid);
relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 1de477cbeeb..7debb14bb5d 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
#include "postgres.h"
+#include "access/htup_details.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
#include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
#include "utils/memutils.h"
#include "utils/pgstat_internal.h"
#include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
#include "utils/timestamp.h"
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
PgStat_Counter inserted_pre_truncdrop;
PgStat_Counter updated_pre_truncdrop;
PgStat_Counter deleted_pre_truncdrop;
- Oid id; /* table's OID */
- bool shared; /* is it a shared catalog? */
+ RelFileLocator locator; /* table's rd_locator */
bool truncdropped; /* was the relation truncated/dropped? */
} TwoPhasePgStatRecord;
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
PgStatShared_Relation *dstshstats;
PgStat_EntryRef *dst_ref;
- srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
- RelationGetRelid(src));
+ srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
if (!srcstats)
return;
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
/*
* We only count stats for relations with storage and partitioned tables
+ * and we don't count stats generated during a rewrite.
*/
- if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+ if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+ OidIsValid(rel->rd_rel->relrewrite))
{
rel->pgstat_enabled = false;
rel->pgstat_info = NULL;
@@ -130,12 +135,38 @@ pgstat_init_relation(Relation rel)
void
pgstat_assoc_relation(Relation rel)
{
+ RelFileLocator locator;
+
Assert(rel->pgstat_enabled);
Assert(rel->pgstat_info == NULL);
+ /*
+ * Don't associate stats for relations without storage and non partitioned
+ * tables.
+ */
+ if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+ rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ return;
+
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ locator = rel->rd_locator;
+ else
+ {
+ /*
+ * Partitioned tables don't have storage, so construct a synthetic
+ * locator for statistics tracking. Use the relation OID as relNumber.
+ * No collision with regular relations is possible because relNumbers
+ * are also assigned from the pg_class OID space (see
+ * GetNewRelFileNumber()), making each value unique across the
+ * database regardless of spcOid.
+ */
+ locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+ locator.spcOid = InvalidOid;
+ locator.relNumber = rel->rd_id;
+ }
+
/* Else find or make the PgStat_TableStatus entry, and update link */
- rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
- rel->rd_rel->relisshared);
+ rel->pgstat_info = pgstat_prep_relation_pending(locator);
/* don't allow link a stats to multiple relcache entries */
Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +198,13 @@ pgstat_unlink_relation(Relation rel)
void
pgstat_create_relation(Relation rel)
{
+ /* don't track stats for relations without storage */
+ if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+ return;
+
pgstat_create_transactional(PGSTAT_KIND_RELATION,
- rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
- RelationGetRelid(rel));
+ rel->rd_locator.dbOid,
+ RelFileLocatorToPgStatObjid(rel->rd_locator));
}
/*
@@ -181,9 +216,13 @@ pgstat_drop_relation(Relation rel)
int nest_level = GetCurrentTransactionNestLevel();
PgStat_TableStatus *pgstat_info;
+ /* don't track stats for relations without storage */
+ if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+ return;
+
pgstat_drop_transactional(PGSTAT_KIND_RELATION,
- rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
- RelationGetRelid(rel));
+ rel->rd_locator.dbOid,
+ RelFileLocatorToPgStatObjid(rel->rd_locator));
if (!pgstat_should_count_relation(rel))
return;
@@ -207,14 +246,12 @@ pgstat_drop_relation(Relation rel)
* Report that the table was just vacuumed and flush IO statistics.
*/
void
-pgstat_report_vacuum(Oid tableoid, bool shared,
- PgStat_Counter livetuples, PgStat_Counter deadtuples,
- TimestampTz starttime)
+pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+ PgStat_Counter deadtuples, TimestampTz starttime)
{
PgStat_EntryRef *entry_ref;
PgStatShared_Relation *shtabentry;
PgStat_StatTabEntry *tabentry;
- Oid dboid = (shared ? InvalidOid : MyDatabaseId);
TimestampTz ts;
PgStat_Counter elapsedtime;
@@ -227,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
/* block acquiring lock for the same reason as pgstat_report_autovac() */
entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
- dboid, tableoid, false);
+ locator.dbOid, RelFileLocatorToPgStatObjid(locator), false);
shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
tabentry = &shtabentry->stats;
@@ -286,9 +323,9 @@ pgstat_report_analyze(Relation rel,
PgStat_EntryRef *entry_ref;
PgStatShared_Relation *shtabentry;
PgStat_StatTabEntry *tabentry;
- Oid dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
TimestampTz ts;
PgStat_Counter elapsedtime;
+ RelFileLocator locator;
if (!pgstat_track_counts)
return;
@@ -326,9 +363,26 @@ pgstat_report_analyze(Relation rel,
ts = GetCurrentTimestamp();
elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ locator = rel->rd_locator;
+ else
+ {
+ /*
+ * Partitioned tables don't have storage, so construct a synthetic
+ * locator for statistics tracking. Use the relation OID as relNumber.
+ * No collision with regular relations is possible because relNumbers
+ * are also assigned from the pg_class OID space (see
+ * GetNewRelFileNumber()), making each value unique across the
+ * database regardless of spcOid.
+ */
+ locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+ locator.spcOid = InvalidOid;
+ locator.relNumber = rel->rd_id;
+ }
/* block acquiring lock for the same reason as pgstat_report_autovac() */
- entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
- RelationGetRelid(rel),
+ entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+ locator.dbOid,
+ RelFileLocatorToPgStatObjid(locator),
false);
/* can't get dropped while accessed */
Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -469,7 +523,7 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
PgStat_StatTabEntry *
pgstat_fetch_stat_tabentry(Oid relid)
{
- return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+ return pgstat_fetch_stat_tabentry_ext(relid);
}
/*
@@ -477,12 +531,19 @@ pgstat_fetch_stat_tabentry(Oid relid)
* whether the to-be-accessed table is a shared relation or not.
*/
PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
{
- Oid dboid = (shared ? InvalidOid : MyDatabaseId);
+ PgStat_StatTabEntry *tabentry;
+ RelFileLocator locator;
+
+ if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+ return NULL;
- return (PgStat_StatTabEntry *)
- pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+ /* fetch the stats entry using the relfilenode based key */
+ tabentry = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION,
+ locator.dbOid,
+ RelFileLocatorToPgStatObjid(locator));
+ return tabentry;
}
/*
@@ -504,14 +565,17 @@ find_tabstat_entry(Oid rel_id)
PgStat_TableXactStatus *trans;
PgStat_TableStatus *tabentry = NULL;
PgStat_TableStatus *tablestatus = NULL;
+ RelFileLocator locator;
+
+ if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+ return NULL;
+
+ entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+ locator.dbOid,
+ RelFileLocatorToPgStatObjid(locator));
- entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
if (!entry_ref)
- {
- entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
- if (!entry_ref)
- return tablestatus;
- }
+ return tablestatus;
tabentry = (PgStat_TableStatus *) entry_ref->pending;
tablestatus = palloc(sizeof(PgStat_TableStatus));
@@ -707,8 +771,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
- record.id = tabstat->id;
- record.shared = tabstat->shared;
+
+ if (tabstat->relation != NULL)
+ record.locator = tabstat->relation->rd_locator;
+ else
+ record.locator = tabstat->locator;
+
record.truncdropped = trans->truncdropped;
RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -751,7 +819,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
PgStat_TableStatus *pgstat_info;
/* Find or create a tabstat entry for the rel */
- pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+ pgstat_info = pgstat_prep_relation_pending(rec->locator);
/* Same math as in AtEOXact_PgStat, commit case */
pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -786,8 +854,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
PgStat_TableStatus *pgstat_info;
- /* Find or create a tabstat entry for the rel */
- pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+ /* Find or create a tabstat entry for the target locator */
+ pgstat_info = pgstat_prep_relation_pending(rec->locator);
/* Same math as in AtEOXact_PgStat, abort case */
if (rec->truncdropped)
@@ -921,17 +989,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
* initialized if not exists.
*/
static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
{
PgStat_EntryRef *entry_ref;
PgStat_TableStatus *pending;
+ uint64 objid;
+
+ objid = RelFileLocatorToPgStatObjid(locator);
entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
- isshared ? InvalidOid : MyDatabaseId,
- rel_id, NULL);
+ locator.dbOid,
+ objid, NULL);
+
pending = entry_ref->pending;
- pending->id = rel_id;
- pending->shared = isshared;
+ pending->id = objid;
+ pending->locator = locator;
return pending;
}
@@ -1010,3 +1082,83 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
trans->tuples_deleted = trans->deleted_pre_truncdrop;
}
}
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+ HeapTuple tuple;
+ Form_pg_class relform;
+ bool result = true;
+
+ /* get the relation's tuple from pg_class */
+ tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+ if (!HeapTupleIsValid(tuple))
+ return false;
+
+ relform = (Form_pg_class) GETSTRUCT(tuple);
+
+ /* skip relations without storage and non partitioned tables */
+ if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+ relform->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ ReleaseSysCache(tuple);
+ return false;
+ }
+
+ if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* build the RelFileLocator */
+ locator->relNumber = relform->relfilenode;
+ locator->spcOid = relform->reltablespace;
+
+ /* handle default tablespace */
+ if (!OidIsValid(locator->spcOid))
+ locator->spcOid = MyDatabaseTableSpace;
+
+ /* handle dbOid for global vs local relations */
+ if (locator->spcOid == GLOBALTABLESPACE_OID)
+ locator->dbOid = InvalidOid;
+ else
+ locator->dbOid = MyDatabaseId;
+
+ /* handle mapped relations */
+ if (!RelFileNumberIsValid(locator->relNumber))
+ {
+ locator->relNumber = RelationMapOidToFilenumber(reloid,
+ relform->relisshared);
+ if (!RelFileNumberIsValid(locator->relNumber))
+ {
+ ReleaseSysCache(tuple);
+ return false;
+ }
+ }
+ }
+ else
+ {
+ /*
+ * Partitioned tables don't have storage, so construct a synthetic
+ * locator for statistics tracking. Use the relation OID as relNumber.
+ * No collision with regular relations is possible because relNumbers
+ * are also assigned from the pg_class OID space (see
+ * GetNewRelFileNumber()), making each value unique across the
+ * database regardless of spcOid.
+ */
+ locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+ locator->spcOid = InvalidOid;
+ locator->relNumber = relform->oid;
+ }
+
+ ReleaseSysCache(tuple);
+ return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index a710508979e..7924cdf5b97 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
#include "common/ip.h"
#include "funcapi.h"
#include "miscadmin.h"
-#include "pgstat.h"
#include "postmaster/bgworker.h"
#include "replication/logicallauncher.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "utils/acl.h"
#include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
#include "utils/timestamp.h"
#define UINT32_ACCESS_ONCE(var) ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
{
Oid taboid = PG_GETARG_OID(0);
- Oid dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+ RelFileLocator locator;
- pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+ /* Get the stats locator from the relation OID */
+ if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+ PG_RETURN_VOID();
+
+ pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+ RelFileLocatorToPgStatObjid(locator));
PG_RETURN_VOID();
}
@@ -2290,5 +2295,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
uint64 objid = PG_GETARG_INT64(2);
PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
+ /* Convert relation OID to relfilenode objid */
+ if (kind == PGSTAT_KIND_RELATION)
+ {
+ RelFileLocator locator;
+
+ if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+ PG_RETURN_BOOL(false);
+
+ objid = RelFileLocatorToPgStatObjid(locator);
+ }
+
PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
}
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 7ae503e71a2..5d0fe79f7e3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
#include "portability/instr_time.h"
#include "postmaster/pgarch.h" /* for MAX_XFN_CHARS */
#include "replication/conflict.h"
+#include "storage/relfilelocator.h"
#include "utils/backend_progress.h" /* for backward compatibility */ /* IWYU pragma: export */
#include "utils/backend_status.h" /* for backward compatibility */ /* IWYU pragma: export */
#include "utils/pgstat_kind.h"
@@ -34,6 +35,12 @@
/* Default directory to store temporary statistics data in */
#define PG_STAT_TMP_DIR "pg_stat_tmp"
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+ (((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
/* Values for track_functions GUC variable --- order is significant! */
typedef enum TrackFunctionsLevel
{
@@ -173,11 +180,11 @@ typedef struct PgStat_TableCounts
*/
typedef struct PgStat_TableStatus
{
- Oid id; /* table's OID */
- bool shared; /* is it a shared catalog? */
+ uint64 id; /* hash of relfilelocator for stats key */
struct PgStat_TableXactStatus *trans; /* lowest subxact's counts */
PgStat_TableCounts counts; /* event counts to be sent */
Relation relation; /* rel that is using this entry */
+ RelFileLocator locator; /* table's relfilelocator */
} PgStat_TableStatus;
/* ----------
@@ -664,8 +671,8 @@ extern void pgstat_init_relation(Relation rel);
extern void pgstat_assoc_relation(Relation rel);
extern void pgstat_unlink_relation(Relation rel);
-extern void pgstat_report_vacuum(Oid tableoid, bool shared,
- PgStat_Counter livetuples, PgStat_Counter deadtuples,
+extern void pgstat_report_vacuum(RelFileLocator locator, PgStat_Counter livetuples,
+ PgStat_Counter deadtuples,
TimestampTz starttime);
extern void pgstat_report_analyze(Relation rel,
PgStat_Counter livetuples, PgStat_Counter deadtuples,
@@ -730,8 +737,7 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
void *recdata, uint32 len);
extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
- Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 4d2b8aa6081..1252249231d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -718,6 +718,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
/*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
# verify stats objects exist
$sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
't', "$sect: relation stats do exist");
# regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
$node->start;
$sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
't', "$sect: relation stats do exist");
$node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
# stats should have been discarded
$sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
'f', "$sect: relation stats do not exist");
# get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
trigger_funcrel_stat();
$sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
't', "$sect: relation stats do exist");
# regular shutdown
@@ -129,10 +129,10 @@ $node->start;
# no stats present due to invalid stats file
$sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
'f', "$sect: relation stats do not exist");
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
$node->start;
$sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
'f', "$sect: relation stats do not exist");
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
sub have_stats
{
- my ($kind, $dboid, $objid) = @_;
+ my ($db, $kind, $dboid, $objid) = @_;
- return $node->safe_psql($connect_db,
+ return $node->safe_psql($db,
"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
}
--
2.34.1
--KMYjwlsACqdYx2P8
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v7-0003-handle-relation-statistics-correctly-during-rewri.patch"
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 221 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 160 insertions(+), 110 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3093,41 +3074,65 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
- chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
- InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-07-15 08:37 Antonin Houska <[email protected]>
0 siblings, 0 replies; 82+ messages in thread
From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw)
This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
src/backend/commands/repack.c | 223 ++++++++++++++++---------------
src/include/commands/repack.h | 48 +++++++
src/tools/pgindent/typedefs.list | 1 +
3 files changed, 161 insertions(+), 111 deletions(-)
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 19927c15bf3..392332b4b2b 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -95,40 +95,6 @@ typedef struct
Oid indexOid;
} RelToCluster;
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT 0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
- /* The relation the changes are applied to. */
- Relation cc_rel;
-
- /* Needed to update indexes of cc_rel. */
- ResultRelInfo *cc_rri;
- EState *cc_estate;
-
- /*
- * Existing tuples to UPDATE and DELETE are located via this index. We
- * keep the scankey in partially initialized state to avoid repeated work.
- * sk_argument is completed on the fly.
- */
- Relation cc_ident_index;
- ScanKey cc_ident_key;
- int cc_ident_key_nentries;
-
- /* The latest column we need to deform to have the tuple identity */
- AttrNumber cc_last_key_attno;
-
- /* Sequential number of the file containing the changes. */
- int cc_file_seq;
-} ChangeContext;
-
/*
* Backend-local information to control the decoding worker.
*/
@@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool repack_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+ TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple);
static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
static void restore_tuple(BufFile *file, Relation relation,
TupleTableSlot *slot);
static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
- TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate);
static void process_concurrent_changes(XLogRecPtr end_of_wal,
ChangeContext *chgcxt,
@@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
Relation relation,
Oid ident_index_id);
static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Oid identIdx,
TransactionId frozenXid,
@@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd)
}
/*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
{
ConcurrentChangeKind kind = '\0';
- Relation rel = chgcxt->cc_rel;
+ RepackDest *dest;
+ Relation rel;
TupleTableSlot *spilled_tuple;
TupleTableSlot *old_update_tuple;
TupleTableSlot *ondisk_tuple;
bool have_old_tuple = false;
MemoryContext oldcxt;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+
+ dest = &chgcxt->cc_dest;
+ rel = dest->rel;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ /* Open the file containing the changes. */
+ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
@@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
&TTSOpsVirtual);
- oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+ oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
while (true)
{
@@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
if (kind == CHANGE_INSERT)
{
- apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+ apply_concurrent_insert(dest, spilled_tuple);
}
else if (kind == CHANGE_DELETE)
{
bool found;
/* Find the tuple to be deleted */
- found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+ found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
apply_concurrent_delete(rel, ondisk_tuple);
@@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
key = spilled_tuple;
/* Find the tuple to be updated or deleted. */
- found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+ found = find_target_tuple(dest, key, ondisk_tuple);
if (!found)
elog(ERROR, "could not find target tuple");
@@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
*/
adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
- apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+ apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
ExecClearTuple(old_update_tuple);
have_old_tuple = false;
@@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
else
elog(ERROR, "unrecognized kind of change: %d", kind);
- ResetPerTupleExprContext(chgcxt->cc_estate);
+ ResetPerTupleExprContext(dest->estate);
}
/* Cleanup. */
@@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
ExecDropSingleTupleTableSlot(old_update_tuple);
MemoryContextSwitchTo(oldcxt);
+
+ BufFileClose(file);
}
/*
@@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
* table.
*/
static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
- ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
{
/* Put the tuple in the table, but make sure it won't be decoded */
- table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+ table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
TABLE_INSERT_NO_LOGICAL, NULL);
/* Update indexes with this new tuple. */
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
0,
slot,
NIL, NULL);
@@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
* table.
*/
static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
- TupleTableSlot *ondisk_tuple,
- ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+ TupleTableSlot *ondisk_tuple)
{
+ Relation rel = dest->rel;
LockTupleMode lockmode;
TM_FailureData tmfd;
TU_UpdateIndexes update_indexes;
@@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
if (update_indexes == TU_Summarizing)
flags |= EIIT_ONLY_SUMMARIZING;
- ExecInsertIndexTuples(chgcxt->cc_rri,
- chgcxt->cc_estate,
+ ExecInsertIndexTuples(dest->rri,
+ dest->estate,
flags,
spilled_tuple,
NIL, NULL);
@@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
* not found, return false.
*/
static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *retrieved)
{
- Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+ Relation rel = dest->rel;
+ Form_pg_index idx = dest->ident_index->rd_index;
IndexScanDesc scan;
bool retval = false;
@@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
*
* Use the incoming tuple to finalize the scan key.
*/
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
+ ScanKey entry = &dest->ident_key[i];
AttrNumber attno = idx->indkey.values[i];
entry->sk_argument = locator->tts_values[attno - 1];
@@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
}
/* XXX no instrumentation for now */
- scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
- NULL, chgcxt->cc_ident_key_nentries, 0, 0);
- index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+ scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0, 0);
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
{
/* Be wary of temporal constraints */
- if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+ if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
{
CHECK_FOR_INTERRUPTS();
continue;
@@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
* used for temporal constraints.
*/
static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
TupleTableSlot *candidate)
{
- slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
- slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+ slot_getsomeattrs(locator, dest->last_key_attno);
+ slot_getsomeattrs(candidate, dest->last_key_attno);
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- ScanKey entry = &chgcxt->cc_ident_key[i];
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ ScanKey entry = &dest->ident_key[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
@@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
/* Open the file. */
DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, chgcxt);
+ apply_concurrent_changes(chgcxt);
BufFileClose(file);
@@ -3097,10 +3078,34 @@ static void
initialize_change_context(ChangeContext *chgcxt,
Relation relation, Oid ident_index_id)
{
- chgcxt->cc_rel = relation;
+ initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+ chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+ release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+ Oid ident_index_id)
+{
+ dest->rel = relation;
+ dest->bistate = GetBulkInsertState();
/* Only initialize fields needed by ExecInsertIndexTuples(). */
- chgcxt->cc_estate = CreateExecutorState();
+ dest->estate = CreateExecutorState();
/*
* Set up a range table for the executor, containing our repacked table as
@@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt,
perminfo->updatedCols = updatedCols;
/* finally we can initialize the range table proper */
- ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos,
+ ExecInitRangeTable(dest->estate, list_make1(rte), perminfos,
bms_make_singleton(1));
}
/* Set up our ResultRelInfo to use for index updates */
- chgcxt->cc_rri = makeNode(ResultRelInfo);
- InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0);
- ExecOpenIndices(chgcxt->cc_rri, false);
+ dest->rri = makeNode(ResultRelInfo);
+ InitResultRelInfo(dest->rri, relation, 1, NULL, 0);
+ ExecOpenIndices(dest->rri, false);
/*
* The table's relcache entry already has the relcache entry for the
* identity index; find that.
*/
- chgcxt->cc_ident_index = NULL;
- for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+ dest->ident_index = NULL;
+ for (int i = 0; i < dest->rri->ri_NumIndices; i++)
{
Relation ind_rel;
- ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+ ind_rel = dest->rri->ri_IndexRelationDescs[i];
if (ind_rel->rd_id == ident_index_id)
{
- chgcxt->cc_ident_index = ind_rel;
+ dest->ident_index = ind_rel;
break;
}
}
- if (chgcxt->cc_ident_index == NULL)
+ if (dest->ident_index == NULL)
elog(ERROR, "could not find identity index");
/* Set up for scanning said identity index */
{
Form_pg_index indexForm;
- indexForm = chgcxt->cc_ident_index->rd_index;
- chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
- chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+ indexForm = dest->ident_index->rd_index;
+ dest->ident_key_nentries = indexForm->indnkeyatts;
+ dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
for (int i = 0; i < indexForm->indnkeyatts; i++)
{
ScanKey entry;
@@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt,
opcode;
StrategyNumber eq_strategy;
- entry = &chgcxt->cc_ident_key[i];
+ entry = &dest->ident_key[i];
- opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
- opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+ opfamily = dest->ident_index->rd_opfamily[i];
+ opcintype = dest->ident_index->rd_opcintype[i];
eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
- chgcxt->cc_ident_index->rd_rel->relam,
+ dest->ident_index->rd_rel->relam,
opfamily, false);
if (eq_strategy == InvalidStrategy)
elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt,
i + 1,
eq_strategy, opcode,
(Datum) 0);
- entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+ entry->sk_collation = dest->ident_index->rd_indcollation[i];
}
}
/* Determine the last column we must deform to read the identity */
- chgcxt->cc_last_key_attno = InvalidAttrNumber;
- for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+ dest->last_key_attno = InvalidAttrNumber;
+ for (int i = 0; i < dest->ident_key_nentries; i++)
{
- AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+ AttrNumber attno = dest->ident_index->rd_index->indkey.values[i];
Assert(attno > 0);
- chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+ dest->last_key_attno = Max(dest->last_key_attno, attno);
}
-
- chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
}
-/*
- * Free up resources taken by a ChangeContext.
- */
static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
{
- ExecCloseIndices(chgcxt->cc_rri);
- FreeExecutorState(chgcxt->cc_estate);
+ FreeBulkInsertState(dest->bistate);
+ ExecCloseIndices(dest->rri);
+ FreeExecutorState(dest->estate);
/* XXX are these pfrees necessary? */
- pfree(chgcxt->cc_rri);
- pfree(chgcxt->cc_ident_key);
+ pfree(dest->rri);
+ pfree(dest->ident_key);
}
/*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
#include <signal.h>
#include "access/hio.h"
+#include "access/skey.h"
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ BulkInsertStateData *bistate;
+
+ /* Needed to update indexes of cc_rel. */
+ ResultRelInfo *rri;
+ EState *estate;
+
+ /*
+ * Existing tuples to UPDATE and DELETE are located via this index. We
+ * keep the scankey in partially initialized state to avoid repeated work.
+ * sk_argument is completed on the fly.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+
+ int ident_key_nentries;
+
+ /* The latest column we need to deform to have the tuple identity */
+ AttrNumber last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT 0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+ /* The destination table. */
+ RepackDest cc_dest;
+
+ /* Sequential number of the file containing the changes. */
+ int cc_file_seq;
+} ChangeContext;
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 56c1f997f88..25ac7079099 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepackCommand
+RepackDest
RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
--
2.52.0
--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch
^ permalink raw reply [nested|flat] 82+ messages in thread
end of thread, other threads:[~2026-07-15 08:37 UTC | newest]
Thread overview: 82+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2025-10-01 09:45 [PATCH v7 2/3] Key PGSTAT_KIND_RELATION by relfile locator Bertrand Drouvot <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox