agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 4/8] Optimize allocations in bringetbitmap 2+ messages / 2 participants [nested] [flat]
* [PATCH 4/8] Optimize allocations in bringetbitmap @ 2021-03-02 18:57 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Tomas Vondra @ 2021-03-02 18:57 UTC (permalink / raw) The bringetbitmap function allocates memory for various purposes, which may be quite expensive, depending on the number of scan keys. Instead of allocating them separately, allocate one bit chunk of memory an carve it into smaller pieces as needed - all the pieces have the same lifespan, and it saves quite a bit of CPU and memory overhead. Author: Tomas Vondra <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 60 ++++++++++++++++++++++++++-------- 1 file changed, 47 insertions(+), 13 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ce0f525c21..758c47f0f4 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -373,6 +373,9 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) int *nkeys, *nnullkeys; int keyno; + char *ptr; + Size len; + char *tmp PG_USED_FOR_ASSERTS_ONLY; opaque = (BrinOpaque *) scan->opaque; bdesc = opaque->bo_bdesc; @@ -402,15 +405,52 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * We keep null and regular keys separate, so that we can pass just the * regular keys to the consistent function easily. * + * To reduce the allocation overhead, we allocate one big chunk and then + * carve it into smaller arrays ourselves. All the pieces have exactly the + * same lifetime, so that's OK. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ - keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); - nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); - nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); - nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + len = + MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) + /* regular keys */ + MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys) * bdesc->bd_tupdesc->natts + + MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts) + + MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) + /* NULL keys */ + MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys) * bdesc->bd_tupdesc->natts + + MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts); + + ptr = palloc(len); + tmp = ptr; + + keys = (ScanKey **) ptr; + ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + + nullkeys = (ScanKey **) ptr; + ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + + nkeys = (int *) ptr; + ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts); + + nnullkeys = (int *) ptr; + ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts); + + for (int i = 0; i < bdesc->bd_tupdesc->natts; i++) + { + keys[i] = (ScanKey *) ptr; + ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[i] = (ScanKey *) ptr; + ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys); + } + + Assert(tmp + len == ptr); + + /* zero the number of keys */ + memset(nkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts); + memset(nnullkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -444,9 +484,9 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) { FmgrInfo *tmp; - /* No key/null arrays for this attribute. */ - Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); - Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); + /* First time we see this attribute, so no key/null keys. */ + Assert(nkeys[keyattno - 1] == 0); + Assert(nnullkeys[keyattno - 1] == 0); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -457,17 +497,11 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* Add key to the proper per-attribute array. */ if (key->sk_flags & SK_ISNULL) { - if (!nullkeys[keyattno - 1]) - nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; nnullkeys[keyattno - 1]++; } else { - if (!keys[keyattno - 1]) - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - keys[keyattno - 1][nkeys[keyattno - 1]] = key; nkeys[keyattno - 1]++; } -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0005-BRIN-bloom-indexes-20210311.patch" Content-Transfer-Encoding: 8bit Content-Disposition: attachment; filename="0005-BRIN-bloom-indexes-20210311.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
* [PATCH 3/6] Move conversion of a "historic" to MVCC snapshot to a separate function. @ 2026-01-22 08:23 Antonin Houska <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Antonin Houska @ 2026-01-22 08:23 UTC (permalink / raw) The conversion is now handled by SnapBuildMVCCFromHistoric(). REPACK CONCURRENTLY will also need it. --- src/backend/replication/logical/snapbuild.c | 59 +++++++++++++++++---- src/backend/utils/time/snapmgr.c | 3 +- src/include/replication/snapbuild.h | 1 + src/include/utils/snapmgr.h | 1 + 4 files changed, 52 insertions(+), 12 deletions(-) diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 7f79621b57e..a738ad8a864 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -440,10 +440,7 @@ Snapshot SnapBuildInitialSnapshot(SnapBuild *builder) { Snapshot snap; - TransactionId xid; TransactionId safeXid; - TransactionId *newxip; - int newxcnt = 0; Assert(XactIsoLevel == XACT_REPEATABLE_READ); Assert(builder->building_full_snapshot); @@ -485,7 +482,35 @@ SnapBuildInitialSnapshot(SnapBuild *builder) MyProc->xmin = snap->xmin; - /* allocate in transaction context */ + /* Convert the historic snapshot to MVCC snapshot. */ + return SnapBuildMVCCFromHistoric(snap, true); +} + +/* + * Turn a historic MVCC snapshot into an ordinary MVCC snapshot. + * + * Unlike a regular (non-historic) MVCC snapshot, the 'xip' array of this + * snapshot contains not only running main transactions, but also their + * subtransactions. On the other hand, 'subxip' will usually be empty. This + * difference does not affect the result of XidInMVCCSnapshot() because it + * searches both in 'xip' and 'subxip'. + * + * Pass true for 'in_place' if you don't care about modifying the source + * snapshot. If you need a new instance, and one that was allocated as a + * single chunk of memory, pass false. + */ +Snapshot +SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place) +{ + TransactionId xid; + TransactionId *oldxip = snapshot->xip; + uint32 oldxcnt = snapshot->xcnt; + TransactionId *newxip; + int newxcnt = 0; + Snapshot result; + + Assert(snapshot->snapshot_type == SNAPSHOT_HISTORIC_MVCC); + newxip = palloc_array(TransactionId, GetMaxSnapshotXidCount()); /* @@ -494,7 +519,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder) * classical snapshot by marking all non-committed transactions as * in-progress. This can be expensive. */ - for (xid = snap->xmin; NormalTransactionIdPrecedes(xid, snap->xmax);) + for (xid = snapshot->xmin; NormalTransactionIdPrecedes(xid, snapshot->xmax);) { void *test; @@ -502,7 +527,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder) * Check whether transaction committed using the decoding snapshot * meaning of ->xip. */ - test = bsearch(&xid, snap->xip, snap->xcnt, + test = bsearch(&xid, snapshot->xip, snapshot->xcnt, sizeof(TransactionId), xidComparator); if (test == NULL) @@ -519,11 +544,25 @@ SnapBuildInitialSnapshot(SnapBuild *builder) } /* adjust remaining snapshot fields as needed */ - snap->snapshot_type = SNAPSHOT_MVCC; - snap->xcnt = newxcnt; - snap->xip = newxip; + snapshot->xcnt = newxcnt; + snapshot->xip = newxip; + + if (in_place) + result = snapshot; + else + { + result = CopySnapshot(snapshot); + + /* Restore the original values so the source is intact. */ + snapshot->xip = oldxip; + snapshot->xcnt = oldxcnt; + + /* newxip has been copied */ + pfree(newxip); + } + result->snapshot_type = SNAPSHOT_MVCC; - return snap; + return result; } /* diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c index 2e6197f5f35..3af1b366adf 100644 --- a/src/backend/utils/time/snapmgr.c +++ b/src/backend/utils/time/snapmgr.c @@ -213,7 +213,6 @@ typedef struct ExportedSnapshot static List *exportedSnapshots = NIL; /* Prototypes for local functions */ -static Snapshot CopySnapshot(Snapshot snapshot); static void UnregisterSnapshotNoOwner(Snapshot snapshot); static void FreeSnapshot(Snapshot snapshot); static void SnapshotResetXmin(void); @@ -604,7 +603,7 @@ SetTransactionSnapshot(Snapshot sourcesnap, VirtualTransactionId *sourcevxid, * The copy is palloc'd in TopTransactionContext and has initial refcounts set * to 0. The returned snapshot has the copied flag set. */ -static Snapshot +Snapshot CopySnapshot(Snapshot snapshot) { Snapshot newsnap; diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h index ccded021433..34383dea776 100644 --- a/src/include/replication/snapbuild.h +++ b/src/include/replication/snapbuild.h @@ -73,6 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder); extern void SnapBuildSnapDecRefcount(Snapshot snap); extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder); +extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place); extern const char *SnapBuildExportSnapshot(SnapBuild *builder); extern void SnapBuildClearExportedSnapshot(void); extern void SnapBuildResetExportedSnapshotState(void); diff --git a/src/include/utils/snapmgr.h b/src/include/utils/snapmgr.h index b8c01a291a1..de824945f0b 100644 --- a/src/include/utils/snapmgr.h +++ b/src/include/utils/snapmgr.h @@ -63,6 +63,7 @@ extern Snapshot GetTransactionSnapshot(void); extern Snapshot GetLatestSnapshot(void); extern void SnapshotSetCommandId(CommandId curcid); +extern Snapshot CopySnapshot(Snapshot snapshot); extern Snapshot GetCatalogSnapshot(Oid relid); extern Snapshot GetNonHistoricCatalogSnapshot(Oid relid); extern void InvalidateCatalogSnapshot(void); -- 2.47.3 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v31-0004-Add-CONCURRENTLY-option-to-REPACK-command.patch ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2026-01-22 08:23 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2021-03-02 18:57 [PATCH 4/8] Optimize allocations in bringetbitmap Tomas Vondra <[email protected]> 2026-01-22 08:23 [PATCH 3/6] Move conversion of a "historic" to MVCC snapshot to a separate function. 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