Thread
-
[PATCH va1 2/2] Mega-WIP: Optimized out/send path for printtup
Andres Freund <andres@anarazel.de> — 2026-05-06T15:44:26Z
Discussion: https://postgr.es/m/877bpghevm.fsf@163.com --- src/include/nodes/miscnodes.h | 12 +++++ src/backend/access/common/printtup.c | 35 +++++++++++-- src/backend/utils/adt/int.c | 73 +++++++++++++++++++++++++--- src/backend/utils/adt/varlena.c | 40 ++++++++++++++- 4 files changed, 148 insertions(+), 12 deletions(-) diff --git a/src/include/nodes/miscnodes.h b/src/include/nodes/miscnodes.h index ec833001ab0..b3c189a5c0c 100644 --- a/src/include/nodes/miscnodes.h +++ b/src/include/nodes/miscnodes.h @@ -54,4 +54,16 @@ typedef struct ErrorSaveContext ((escontext) != NULL && IsA(escontext, ErrorSaveContext) && \ ((ErrorSaveContext *) (escontext))->error_occurred) + +/* + * Type optionally passed to input/receive/output/send functions that allows + * those functions to opt into more efficient ways of performing their work + * (mainly reducing allocations & copies). + */ +typedef struct InOutContext +{ + NodeTag type; + StringInfo buf; +} InOutContext; + #endif /* MISCNODES_H */ diff --git a/src/backend/access/common/printtup.c b/src/backend/access/common/printtup.c index 6fa93a6798a..2e3eb8f56d3 100644 --- a/src/backend/access/common/printtup.c +++ b/src/backend/access/common/printtup.c @@ -63,6 +63,7 @@ typedef struct int nattrs; PrinttupAttrInfo *myinfo; /* Cached info about each attr */ StringInfoData buf; /* output buffer (*not* in tmpcontext) */ + InOutContext inout; /* FunctionCallInfo->context data */ MemoryContext tmpcontext; /* Memory context for per-row workspace */ } DR_printtup; @@ -142,6 +143,9 @@ printtup_startup(DestReceiver *self, int operation, TupleDesc typeinfo) FetchPortalTargetList(portal), portal->formats); + myState->inout.type = T_InOutContext; + myState->inout.buf = &myState->buf; + /* ---------------- * We could set up the derived attr info at this time, but we postpone it * until the first call of printtup, for 2 reasons: @@ -297,6 +301,15 @@ printtup_prepare_info(DR_printtup *myState, TupleDesc typeinfo, int numAttrs) /* both out and send funcs have one argument */ thisState->outstate = palloc0(SizeForFunctionCallInfo(1)); thisState->outstate->flinfo = &thisState->finfo; + + /* + * The idea here is that output functions can optionally use more + * efficient paths if they see that the context is InOutContext, by + * directly appending correctly formatted output into the output + * buffer. + */ + thisState->outstate->context = (Node *) &myState->inout; + thisState->outstate->nargs = 1; } } @@ -369,7 +382,13 @@ printtup(TupleTableSlot *slot, DestReceiver *self) outputstr = DatumGetCString(FunctionCallInvoke(thisState->outstate)); Assert(!thisState->outstate->isnull); - pq_sendcountedtext(buf, outputstr, strlen(outputstr)); + + /* + * If outputstr == NULL, the output function directly appended a + * correctly formatted message. + */ + if (outputstr) + pq_sendcountedtext(buf, outputstr, strlen(outputstr)); } else { @@ -378,9 +397,17 @@ printtup(TupleTableSlot *slot, DestReceiver *self) outputbytes = DatumGetByteaP(FunctionCallInvoke(thisState->outstate)); Assert(!thisState->outstate->isnull); - pq_sendint32(buf, VARSIZE(outputbytes) - VARHDRSZ); - pq_sendbytes(buf, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); + + /* + * If outputbytes == NULL, the send function directly appended a + * correctly formatted message. + */ + if (outputbytes) + { + pq_sendint32(buf, VARSIZE(outputbytes) - VARHDRSZ); + pq_sendbytes(buf, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } } } diff --git a/src/backend/utils/adt/int.c b/src/backend/utils/adt/int.c index 4c894a49d5d..1b7b5b5246c 100644 --- a/src/backend/utils/adt/int.c +++ b/src/backend/utils/adt/int.c @@ -327,10 +327,54 @@ Datum int4out(PG_FUNCTION_ARGS) { int32 arg1 = PG_GETARG_INT32(0); - char *result = (char *) palloc(12); /* sign, 10 digits, '\0' */ + int maxlen = 12; /* sign, 10 digits, '\0' */ - pg_ltoa(arg1, result); - PG_RETURN_CSTRING(result); + if (fcinfo->context && IsA(fcinfo->context, InOutContext)) + { + /* + * Optimized path for output functions called as part of a larger + * ouput. + * + * FIXME: A good chunk of this should obviously be in helper + * functions. + */ + InOutContext *inout = castNode(InOutContext, fcinfo->context); + StringInfo buf = inout->buf; + int prev_buflen; + int len; + uint32 len_net; + + /* reserve space for length and the max string length */ + enlargeStringInfo(buf, sizeof(uint32) + maxlen); + + /* reserve space for length, to be filled out later */ + prev_buflen = buf->len; + buf->len += sizeof(uint32); + + /* + * Construct string directly in buffer, we don't have to care about + * encoding conversions, because we assume that every encoding + * embodies ascii (XXX: Is that actually true with client encodings?). + */ + len = pg_ltoa(arg1, buf->data + buf->len); + buf->len += len; + + /* update the previously reserved length */ + len_net = pg_hton32(len); + memcpy(&buf->data[prev_buflen], &len_net, sizeof(uint32)); + + PG_RETURN_VOID(); + } + else + { + /* + * Fallback path called in any other context. + */ + char *result = (char *) palloc(maxlen); + + pg_ltoa(arg1, result); + PG_RETURN_CSTRING(result); + } } /* @@ -351,11 +395,26 @@ Datum int4send(PG_FUNCTION_ARGS) { int32 arg1 = PG_GETARG_INT32(0); - StringInfoData buf; - pq_begintypsend(&buf); - pq_sendint32(&buf, arg1); - PG_RETURN_BYTEA_P(pq_endtypsend(&buf)); + if (fcinfo->context && IsA(fcinfo->context, InOutContext)) + { + InOutContext *inout = castNode(InOutContext, fcinfo->context); + + /* length of data */ + pq_sendint32(inout->buf, 4); + /* data itself */ + pq_sendint32(inout->buf, arg1); + + PG_RETURN_VOID(); + } + else + { + StringInfoData buf; + + pq_begintypsend(&buf); + pq_sendint32(&buf, arg1); + PG_RETURN_BYTEA_P(pq_endtypsend(&buf)); + } } diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c index c0ff51bd2fc..09913bc01f5 100644 --- a/src/backend/utils/adt/varlena.c +++ b/src/backend/utils/adt/varlena.c @@ -290,7 +290,45 @@ textout(PG_FUNCTION_ARGS) { Datum txt = PG_GETARG_DATUM(0); - PG_RETURN_CSTRING(TextDatumGetCString(txt)); + if (fcinfo->context && IsA(fcinfo->context, InOutContext)) + { + StringInfo buf = castNode(InOutContext, fcinfo->context)->buf; + text *tunpacked = pg_detoast_datum_packed(DatumGetPointer(txt)); + int len = VARSIZE_ANY_EXHDR(tunpacked); + char *data = VARDATA_ANY(tunpacked); + char *data_converted; + size_t data_len; + + /* + * Convert text output to the right encoding. For efficiency, this + * should really happen directly into buf. For that we would have to + * reserve space for the length first and fill it out after + * conversion. + * + * FIXME: Obviously we would need helpers for this too. + */ + data_converted = pg_server_to_client(data, len); + + if (data == data_converted) + data_len = len; + else + data_len = strlen(data_converted); + + /* length */ + pq_sendint32(buf, data_len); + + /* actual data */ + appendBinaryStringInfoNT(buf, data_converted, data_len); + + if (tunpacked != DatumGetPointer(txt)) + pfree(tunpacked); + + PG_RETURN_VOID(); + } + else + { + PG_RETURN_CSTRING(TextDatumGetCString(txt)); + } } /* -- 2.46.0.519.g2e7b89e038 --benhmb75h34eqzc4--