On 7/16/20 2:14 PM, Amit Langote wrote:
Amit Langote EnterpriseDB: http://www.enterprisedb.com
Version 5 of the patch. With changes caused by Amit's comments. -- regards, Andrey Lepikhov Postgres Professional
>From 24465d61d6f0ec6a45578d252bda1690ac045543 Mon Sep 17 00:00:00 2001 From: Andrey Lepikhov <a.lepik...@postgrespro.ru> Date: Thu, 9 Jul 2020 11:16:56 +0500 Subject: [PATCH] Fast COPY FROM into the foreign or sharded table. This feature enables bulk COPY into foreign table in the case of multi inserts is possible and foreign table has non-zero number of columns. FDWAPI was extended by next routines: * BeginForeignCopyIn * EndForeignCopyIn * ExecForeignCopyIn BeginForeignCopyIn and EndForeignCopyIn initialize and free the CopyState of bulk COPY. The ExecForeignCopyIn routine send 'COPY ... FROM STDIN' command to the foreign server, in iterative manner send tuples by CopyTo() machinery, send EOF to this connection. Code that constructed list of columns for a given foreign relation in the deparseAnalyzeSql() routine is separated to the deparseRelColumnList(). It is reused in the deparseCopyFromSql(). Added TAP-tests on the specific corner cases of COPY FROM STDIN operation. By the analogy of CopyFrom() the CopyState structure was extended with data_dest_cb callback. It is used for send text representation of a tuple to a custom destination. The PgFdwModifyState structure is extended with the cstate field. It is needed for avoid repeated initialization of CopyState. ALso for this reason CopyTo() routine was split into the set of routines CopyToStart()/ CopyTo()/CopyToFinish(). Discussion: https://www.postgresql.org/message-id/flat/3d0909dc-3691-a576-208a-90986e55489f%40postgrespro.ru Authors: Andrey Lepikhov, Ashutosh Bapat, Amit Langote --- contrib/postgres_fdw/deparse.c | 60 ++++- .../postgres_fdw/expected/postgres_fdw.out | 33 ++- contrib/postgres_fdw/postgres_fdw.c | 146 +++++++++++ contrib/postgres_fdw/postgres_fdw.h | 1 + contrib/postgres_fdw/sql/postgres_fdw.sql | 28 ++ doc/src/sgml/fdwhandler.sgml | 74 ++++++ src/backend/commands/copy.c | 247 +++++++++++------- src/backend/executor/execMain.c | 1 + src/backend/executor/execPartition.c | 34 ++- src/include/commands/copy.h | 11 + src/include/foreign/fdwapi.h | 15 ++ src/include/nodes/execnodes.h | 8 + 12 files changed, 547 insertions(+), 111 deletions(-) diff --git a/contrib/postgres_fdw/deparse.c b/contrib/postgres_fdw/deparse.c index ad37a74221..a37981ff66 100644 --- a/contrib/postgres_fdw/deparse.c +++ b/contrib/postgres_fdw/deparse.c @@ -184,6 +184,8 @@ static void appendAggOrderBy(List *orderList, List *targetList, static void appendFunctionName(Oid funcid, deparse_expr_cxt *context); static Node *deparseSortGroupClause(Index ref, List *tlist, bool force_colno, deparse_expr_cxt *context); +static List *deparseRelColumnList(StringInfo buf, Relation rel, + bool enclose_in_parens); /* * Helper functions @@ -1758,6 +1760,20 @@ deparseInsertSql(StringInfo buf, RangeTblEntry *rte, withCheckOptionList, returningList, retrieved_attrs); } +/* + * Deparse COPY FROM into given buf. + * We need to use list of parameters at each query. + */ +void +deparseCopyFromSql(StringInfo buf, Relation rel) +{ + appendStringInfoString(buf, "COPY "); + deparseRelation(buf, rel); + (void) deparseRelColumnList(buf, rel, true); + + appendStringInfoString(buf, " FROM STDIN "); +} + /* * deparse remote UPDATE statement * @@ -2061,6 +2077,30 @@ deparseAnalyzeSizeSql(StringInfo buf, Relation rel) */ void deparseAnalyzeSql(StringInfo buf, Relation rel, List **retrieved_attrs) +{ + appendStringInfoString(buf, "SELECT "); + *retrieved_attrs = deparseRelColumnList(buf, rel, false); + + /* Don't generate bad syntax for zero-column relation. */ + if (list_length(*retrieved_attrs) == 0) + appendStringInfoString(buf, "NULL"); + + /* + * Construct FROM clause + */ + appendStringInfoString(buf, " FROM "); + deparseRelation(buf, rel); +} + +/* + * Construct the list of columns of given foreign relation in the order they + * appear in the tuple descriptor of the relation. Ignore any dropped columns. + * Use column names on the foreign server instead of local names. + * + * Optionally enclose the list in parantheses. + */ +static List * +deparseRelColumnList(StringInfo buf, Relation rel, bool enclose_in_parens) { Oid relid = RelationGetRelid(rel); TupleDesc tupdesc = RelationGetDescr(rel); @@ -2069,10 +2109,8 @@ deparseAnalyzeSql(StringInfo buf, Relation rel, List **retrieved_attrs) List *options; ListCell *lc; bool first = true; + List *retrieved_attrs = NIL; - *retrieved_attrs = NIL; - - appendStringInfoString(buf, "SELECT "); for (i = 0; i < tupdesc->natts; i++) { /* Ignore dropped columns. */ @@ -2081,6 +2119,9 @@ deparseAnalyzeSql(StringInfo buf, Relation rel, List **retrieved_attrs) if (!first) appendStringInfoString(buf, ", "); + else if (enclose_in_parens) + appendStringInfoChar(buf, '('); + first = false; /* Use attribute name or column_name option. */ @@ -2100,18 +2141,13 @@ deparseAnalyzeSql(StringInfo buf, Relation rel, List **retrieved_attrs) appendStringInfoString(buf, quote_identifier(colname)); - *retrieved_attrs = lappend_int(*retrieved_attrs, i + 1); + retrieved_attrs = lappend_int(retrieved_attrs, i + 1); } - /* Don't generate bad syntax for zero-column relation. */ - if (first) - appendStringInfoString(buf, "NULL"); + if (enclose_in_parens && list_length(retrieved_attrs) > 0) + appendStringInfoChar(buf, ')'); - /* - * Construct FROM clause - */ - appendStringInfoString(buf, " FROM "); - deparseRelation(buf, rel); + return retrieved_attrs; } /* diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..baadb4ea80 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -8063,8 +8063,9 @@ copy rem2 from stdin; copy rem2 from stdin; -- ERROR ERROR: new row for relation "loc2" violates check constraint "loc2_f1positive" DETAIL: Failing row contains (-1, xyzzy). -CONTEXT: remote SQL command: INSERT INTO public.loc2(f1, f2) VALUES ($1, $2) -COPY rem2, line 1: "-1 xyzzy" +CONTEXT: COPY loc2, line 1: "-1 xyzzy" +remote SQL command: COPY public.loc2(f1, f2) FROM STDIN +COPY rem2, line 2 select * from rem2; f1 | f2 ----+----- @@ -8183,6 +8184,34 @@ drop trigger rem2_trig_row_before on rem2; drop trigger rem2_trig_row_after on rem2; drop trigger loc2_trig_row_before_insert on loc2; delete from rem2; +alter table loc2 drop column f1; +alter table loc2 drop column f2; +copy rem2 from stdin; +ERROR: column "f1" of relation "loc2" does not exist +CONTEXT: remote SQL command: COPY public.loc2(f1, f2) FROM STDIN +COPY rem2, line 3 +alter table loc2 add column f1 int; +alter table loc2 add column f2 int; +select * from rem2; + f1 | f2 +----+---- +(0 rows) + +-- dropped columns locally and on the foreign server +alter table rem2 drop column f1; +alter table rem2 drop column f2; +copy rem2 from stdin; +select * from rem2; +-- +(2 rows) + +alter table loc2 drop column f1; +alter table loc2 drop column f2; +copy rem2 from stdin; +select * from rem2; +-- +(4 rows) + -- test COPY FROM with foreign table created in the same transaction create table loc3 (f1 int, f2 text); begin; diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..a314821fb0 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -18,6 +18,7 @@ #include "access/sysattr.h" #include "access/table.h" #include "catalog/pg_class.h" +#include "commands/copy.h" #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" @@ -190,6 +191,7 @@ typedef struct PgFdwModifyState /* for update row movement if subplan result rel */ struct PgFdwModifyState *aux_fmstate; /* foreign-insert state, if * created */ + CopyState cstate; /* foreign COPY state, if used */ } PgFdwModifyState; /* @@ -356,6 +358,13 @@ static void postgresBeginForeignInsert(ModifyTableState *mtstate, ResultRelInfo *resultRelInfo); static void postgresEndForeignInsert(EState *estate, ResultRelInfo *resultRelInfo); +static void postgresBeginForeignCopyIn(ModifyTableState *mtstate, + ResultRelInfo *resultRelInfo); +static void postgresEndForeignCopyIn(EState *estate, + ResultRelInfo *resultRelInfo); +static void postgresExecForeignCopyIn(ResultRelInfo *resultRelInfo, + TupleTableSlot **slots, + int nslots); static int postgresIsForeignRelUpdatable(Relation rel); static bool postgresPlanDirectModify(PlannerInfo *root, ModifyTable *plan, @@ -533,6 +542,9 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->EndForeignModify = postgresEndForeignModify; routine->BeginForeignInsert = postgresBeginForeignInsert; routine->EndForeignInsert = postgresEndForeignInsert; + routine->BeginForeignCopyIn = postgresBeginForeignCopyIn; + routine->EndForeignCopyIn = postgresEndForeignCopyIn; + routine->ExecForeignCopyIn = postgresExecForeignCopyIn; routine->IsForeignRelUpdatable = postgresIsForeignRelUpdatable; routine->PlanDirectModify = postgresPlanDirectModify; routine->BeginDirectModify = postgresBeginDirectModify; @@ -1847,6 +1859,9 @@ postgresExecForeignInsert(EState *estate, PgFdwModifyState *fmstate = (PgFdwModifyState *) resultRelInfo->ri_FdwState; TupleTableSlot *rslot; + Assert(!resultRelInfo->ri_usesBulkModify || + resultRelInfo->ri_FdwRoutine->BeginForeignCopyIn == NULL); + /* * If the fmstate has aux_fmstate set, use the aux_fmstate (see * postgresBeginForeignInsert()) @@ -2051,6 +2066,137 @@ postgresEndForeignInsert(EState *estate, finish_foreign_modify(fmstate); } +static PgFdwModifyState *copy_fmstate = NULL; + +static void +pgfdw_copy_dest_cb(void *buf, int len) +{ + PGconn *conn = copy_fmstate->conn; + + if (PQputCopyData(conn, (char *) buf, len) <= 0) + { + PGresult *res = PQgetResult(conn); + + pgfdw_report_error(ERROR, res, conn, true, copy_fmstate->query); + } +} + +/* + * + * postgresBeginForeignCopyIn + * Begin an COPY operation on a foreign table + */ +static void +postgresBeginForeignCopyIn(ModifyTableState *mtstate, + ResultRelInfo *resultRelInfo) +{ + PgFdwModifyState *fmstate; + StringInfoData sql; + RangeTblEntry *rte; + Relation rel = resultRelInfo->ri_RelationDesc; + + rte = exec_rt_fetch(resultRelInfo->ri_RangeTableIndex, mtstate->ps.state); + initStringInfo(&sql); + deparseCopyFromSql(&sql, rel); + + fmstate = create_foreign_modify(mtstate->ps.state, + rte, + resultRelInfo, + CMD_INSERT, + NULL, + sql.data, + NIL, + false, + NIL); + + fmstate->cstate = BeginCopyTo(NULL, NULL, RelationGetDescr(rel), NULL, + InvalidOid, NULL, false, pgfdw_copy_dest_cb, + NIL, NIL); + CopyToStart(fmstate->cstate); + resultRelInfo->ri_FdwState = fmstate; +} + +/* + * postgresEndForeignCopyIn + * Finish an COPY operation on a foreign table + */ +static void +postgresEndForeignCopyIn(EState *estate, ResultRelInfo *resultRelInfo) +{ + PgFdwModifyState *fmstate = (PgFdwModifyState *) resultRelInfo->ri_FdwState; + + /* Check correct use of CopyIn FDW API. */ + Assert(fmstate->cstate != NULL); + CopyToFinish(fmstate->cstate); + pfree(fmstate->cstate); + fmstate->cstate = NULL; + finish_foreign_modify(fmstate); +} + +/* + * + * postgresExecForeignCopyIn + * Send a number of tuples to the foreign relation. + */ +static void +postgresExecForeignCopyIn(ResultRelInfo *resultRelInfo, + TupleTableSlot **slots, int nslots) +{ + PgFdwModifyState *fmstate = resultRelInfo->ri_FdwState; + PGresult *res; + PGconn *conn = fmstate->conn; + bool status = false; + int i; + + /* Check correct use of CopyIn FDW API. */ + Assert(fmstate->cstate != NULL); + Assert(copy_fmstate == NULL); + + res = PQexec(conn, fmstate->query); + if (PQresultStatus(res) != PGRES_COPY_IN) + pgfdw_report_error(ERROR, res, conn, true, fmstate->query); + PQclear(res); + + PG_TRY(); + { + copy_fmstate = fmstate; + for (i = 0; i < nslots; i++) + CopyOneRowTo(fmstate->cstate, slots[i]); + + status = true; + } + PG_FINALLY(); + { + copy_fmstate = NULL; /* Detect problems */ + + /* Finish COPY IN protocol. It is needed to do after successful copy or + * after an error. + */ + if (PQputCopyEnd(conn, status ? NULL : _("canceled by server")) <= 0 || + PQflush(conn)) + ereport(ERROR, + (errmsg("error returned by PQputCopyEnd: %s", + PQerrorMessage(conn)))); + + /* After successfully sending an EOF signal, check command status. */ + res = PQgetResult(conn); + if ((!status && PQresultStatus(res) != PGRES_FATAL_ERROR) || + (status && PQresultStatus(res) != PGRES_COMMAND_OK)) + pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + + PQclear(res); + /* Do this to ensure we've pumped libpq back to idle state */ + if (PQgetResult(conn) != NULL) + ereport(ERROR, + (errmsg("unexpected extra results during COPY of table: %s", + PQerrorMessage(conn)))); + + if (!status) + PG_RE_THROW(); + } + PG_END_TRY(); +} + /* * postgresIsForeignRelUpdatable * Determine whether a foreign table supports INSERT, UPDATE and/or diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..8fc5ff018f 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -162,6 +162,7 @@ extern void deparseInsertSql(StringInfo buf, RangeTblEntry *rte, List *targetAttrs, bool doNothing, List *withCheckOptionList, List *returningList, List **retrieved_attrs); +extern void deparseCopyFromSql(StringInfo buf, Relation rel); extern void deparseUpdateSql(StringInfo buf, RangeTblEntry *rte, Index rtindex, Relation rel, List *targetAttrs, diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..73f98a3152 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -2293,6 +2293,34 @@ drop trigger loc2_trig_row_before_insert on loc2; delete from rem2; +alter table loc2 drop column f1; +alter table loc2 drop column f2; +copy rem2 from stdin; +1 foo +2 bar +\. + +alter table loc2 add column f1 int; +alter table loc2 add column f2 int; +select * from rem2; + +-- dropped columns locally and on the foreign server +alter table rem2 drop column f1; +alter table rem2 drop column f2; +copy rem2 from stdin; + + +\. +select * from rem2; + +alter table loc2 drop column f1; +alter table loc2 drop column f2; +copy rem2 from stdin; + + +\. +select * from rem2; + -- test COPY FROM with foreign table created in the same transaction create table loc3 (f1 int, f2 text); begin; diff --git a/doc/src/sgml/fdwhandler.sgml b/doc/src/sgml/fdwhandler.sgml index 74793035d7..e8fd91a7bc 100644 --- a/doc/src/sgml/fdwhandler.sgml +++ b/doc/src/sgml/fdwhandler.sgml @@ -795,6 +795,80 @@ EndForeignInsert(EState *estate, <para> <programlisting> +void +BeginForeignCopyIn(ModifyTableState *mtstate, + ResultRelInfo *rinfo); +</programlisting> + + Begin executing an copy operation on a foreign table. This routine is + called right before the first call of <function>ExecForeignCopyIn</function> + routine for the foreign table. It should perform any initialization needed + prior to the actual COPY FROM operation. + Subsequently, <function>ExecForeignCopyIn</function> will be called for + a bulk of tuples to be copied into the foreign table. + </para> + + <para> + <literal>mtstate</literal> is the overall state of the + <structname>ModifyTable</structname> plan node being executed; global data about + the plan and execution state is available via this structure. + <literal>rinfo</literal> is the <structname>ResultRelInfo</structname> struct describing + the target foreign table. (The <structfield>ri_FdwState</structfield> field of + <structname>ResultRelInfo</structname> is available for the FDW to store any + private state it needs for this operation.) + </para> + + <para> + When this is called by a <command>COPY FROM</command> command, the + plan-related global data in <literal>mtstate</literal> is not provided. + </para> + + <para> + If the <function>BeginForeignCopyIn</function> pointer is set to + <literal>NULL</literal>, no action is taken for the initialization. + </para> + + <para> +void +EndForeignCopyIn(EState *estate, + ResultRelInfo *rinfo); +</programlisting> + + End the copy operation and release resources. It is normally not important + to release palloc'd memory, but for example open files and connections + to remote servers should be cleaned up. + </para> + + <para> + If the <function>EndForeignCopyIn</function> pointer is set to + <literal>NULL</literal>, no action is taken for the termination. + </para> + + <para> +<programlisting> +TupleTableSlot * +ExecForeignCopyIn(ResultRelInfo *rinfo, + TupleTableSlot **slots, + int nslots); +</programlisting> + + Copy a bulk of tuples into the foreign table. + <literal>estate</literal> is global execution state for the query. + <literal>rinfo</literal> is the <structname>ResultRelInfo</structname> struct describing + the target foreign table. + <literal>slots</literal> contains the tuples to be inserted; it will match the + row-type definition of the foreign table. + <literal>nslots</literal> cis a number of tuples in the <literal>slots</literal> + </para> + + <para> + If the <function>ExecForeignCopyIn</function> pointer is set to + <literal>NULL</literal>, attempts to insert into the foreign table will fail + with an error message. + </para> + + <para> +<programlisting> int IsForeignRelUpdatable(Relation rel); </programlisting> diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c index 44da71c4cb..2d184b2eee 100644 --- a/src/backend/commands/copy.c +++ b/src/backend/commands/copy.c @@ -128,11 +128,14 @@ typedef struct CopyStateData /* parameters from the COPY command */ Relation rel; /* relation to copy to or from */ + TupleDesc tupDesc; /* COPY TO will be used for manual tuple copying + * into the destination */ QueryDesc *queryDesc; /* executable query to copy from */ List *attnumlist; /* integer list of attnums to copy */ char *filename; /* filename, or NULL for STDIN/STDOUT */ bool is_program; /* is 'filename' a program to popen? */ copy_data_source_cb data_source_cb; /* function for reading data */ + copy_data_dest_cb data_dest_cb; /* function for writing data */ bool binary; /* binary format? */ bool freeze; /* freeze rows on loading? */ bool csv_mode; /* Comma Separated Value format? */ @@ -355,17 +358,12 @@ static const char BinarySignature[11] = "PGCOPY\n\377\r\n\0"; /* non-export function prototypes */ static CopyState BeginCopy(ParseState *pstate, bool is_from, Relation rel, - RawStmt *raw_query, Oid queryRelId, List *attnamelist, - List *options); + TupleDesc srcTupDesc, RawStmt *raw_query, + Oid queryRelId, List *attnamelist, List *options); static void EndCopy(CopyState cstate); static void ClosePipeToProgram(CopyState cstate); -static CopyState BeginCopyTo(ParseState *pstate, Relation rel, RawStmt *query, - Oid queryRelId, const char *filename, bool is_program, - List *attnamelist, List *options); -static void EndCopyTo(CopyState cstate); static uint64 DoCopyTo(CopyState cstate); static uint64 CopyTo(CopyState cstate); -static void CopyOneRowTo(CopyState cstate, TupleTableSlot *slot); static bool CopyReadLine(CopyState cstate); static bool CopyReadLineText(CopyState cstate); static int CopyReadAttributesText(CopyState cstate); @@ -589,7 +587,8 @@ CopySendEndOfRow(CopyState cstate) (void) pq_putmessage('d', fe_msgbuf->data, fe_msgbuf->len); break; case COPY_CALLBACK: - Assert(false); /* Not yet supported. */ + CopySendChar(cstate, '\n'); + cstate->data_dest_cb(fe_msgbuf->data, fe_msgbuf->len); break; } @@ -1076,8 +1075,8 @@ DoCopy(ParseState *pstate, const CopyStmt *stmt, } else { - cstate = BeginCopyTo(pstate, rel, query, relid, - stmt->filename, stmt->is_program, + cstate = BeginCopyTo(pstate, rel, NULL, query, relid, + stmt->filename, stmt->is_program, NULL, stmt->attlist, stmt->options); *processed = DoCopyTo(cstate); /* copy from database to file */ EndCopyTo(cstate); @@ -1459,6 +1458,7 @@ static CopyState BeginCopy(ParseState *pstate, bool is_from, Relation rel, + TupleDesc srcTupDesc, RawStmt *raw_query, Oid queryRelId, List *attnamelist, @@ -1494,6 +1494,11 @@ BeginCopy(ParseState *pstate, tupDesc = RelationGetDescr(cstate->rel); } + else if (srcTupDesc) + { + Assert(!raw_query && !is_from); + tupDesc = cstate->tupDesc = srcTupDesc; + } else { List *rewritten; @@ -1820,20 +1825,25 @@ EndCopy(CopyState cstate) /* * Setup CopyState to read tuples from a table or a query for COPY TO. */ -static CopyState +CopyState BeginCopyTo(ParseState *pstate, Relation rel, + TupleDesc tupDesc, RawStmt *query, Oid queryRelId, const char *filename, bool is_program, + copy_data_dest_cb data_dest_cb, List *attnamelist, List *options) { CopyState cstate; - bool pipe = (filename == NULL); + bool pipe = (filename == NULL) && (data_dest_cb == NULL); MemoryContext oldcontext; + /* Impossible to mix CopyTo modes */ + Assert(rel == NULL || tupDesc == NULL); + if (rel != NULL && rel->rd_rel->relkind != RELKIND_RELATION) { if (rel->rd_rel->relkind == RELKIND_VIEW) @@ -1872,8 +1882,9 @@ BeginCopyTo(ParseState *pstate, RelationGetRelationName(rel)))); } - cstate = BeginCopy(pstate, false, rel, query, queryRelId, attnamelist, - options); + cstate = BeginCopy(pstate, false, rel, tupDesc, query, queryRelId, + attnamelist, options); + oldcontext = MemoryContextSwitchTo(cstate->copycontext); if (pipe) @@ -1882,6 +1893,11 @@ BeginCopyTo(ParseState *pstate, if (whereToSendOutput != DestRemote) cstate->copy_file = stdout; } + else if (data_dest_cb) + { + cstate->copy_dest = COPY_CALLBACK; + cstate->data_dest_cb = data_dest_cb; + } else { cstate->filename = pstrdup(filename); @@ -1968,7 +1984,9 @@ DoCopyTo(CopyState cstate) if (fe_copy) SendCopyBegin(cstate); + CopyToStart(cstate); processed = CopyTo(cstate); + CopyToFinish(cstate); if (fe_copy) SendCopyEnd(cstate); @@ -1991,7 +2009,7 @@ DoCopyTo(CopyState cstate) /* * Clean up storage and release resources for COPY TO. */ -static void +void EndCopyTo(CopyState cstate) { if (cstate->queryDesc != NULL) @@ -2007,19 +2025,22 @@ EndCopyTo(CopyState cstate) EndCopy(cstate); } -/* - * Copy from relation or query TO file. +/* Start COPY TO operation. + * Separated to the routine to prevent duplicate operations in the case of + * manual mode, where tuples are copied to the destination one by one, by call of + * the CopyOneRowTo() routine. */ -static uint64 -CopyTo(CopyState cstate) +void +CopyToStart(CopyState cstate) { TupleDesc tupDesc; int num_phys_attrs; ListCell *cur; - uint64 processed; if (cstate->rel) tupDesc = RelationGetDescr(cstate->rel); + else if (cstate->tupDesc) + tupDesc = cstate->tupDesc; else tupDesc = cstate->queryDesc->tupDesc; num_phys_attrs = tupDesc->natts; @@ -2106,6 +2127,32 @@ CopyTo(CopyState cstate) CopySendEndOfRow(cstate); } } +} + +/* + * Finish COPY TO operation. + */ +void +CopyToFinish(CopyState cstate) +{ + if (cstate->binary) + { + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); + } + + MemoryContextDelete(cstate->rowcontext); +} + +/* + * Copy from relation or query TO file. + */ +static uint64 +CopyTo(CopyState cstate) +{ + uint64 processed; if (cstate->rel) { @@ -2137,24 +2184,13 @@ CopyTo(CopyState cstate) ExecutorRun(cstate->queryDesc, ForwardScanDirection, 0L, true); processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - - if (cstate->binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } - - MemoryContextDelete(cstate->rowcontext); - return processed; } /* * Emit one row during CopyTo(). */ -static void +void CopyOneRowTo(CopyState cstate, TupleTableSlot *slot) { bool need_delim = false; @@ -2447,53 +2483,64 @@ CopyMultiInsertBufferFlush(CopyMultiInsertInfo *miinfo, cstate->line_buf_valid = false; save_cur_lineno = cstate->cur_lineno; - /* - * table_multi_insert may leak memory, so switch to short-lived memory - * context before calling it. - */ - oldcontext = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate)); - table_multi_insert(resultRelInfo->ri_RelationDesc, - slots, - nused, - mycid, - ti_options, - buffer->bistate); - MemoryContextSwitchTo(oldcontext); - - for (i = 0; i < nused; i++) + if (resultRelInfo->ri_RelationDesc->rd_rel->relkind == RELKIND_FOREIGN_TABLE) + { + /* Flush into foreign table or partition */ + resultRelInfo->ri_FdwRoutine->ExecForeignCopyIn(resultRelInfo, + slots, + nused); + } + else { /* - * If there are any indexes, update them for all the inserted tuples, - * and run AFTER ROW INSERT triggers. + * table_multi_insert may leak memory, so switch to short-lived memory + * context before calling it. */ - if (resultRelInfo->ri_NumIndices > 0) - { - List *recheckIndexes; - - cstate->cur_lineno = buffer->linenos[i]; - recheckIndexes = - ExecInsertIndexTuples(buffer->slots[i], estate, false, NULL, - NIL); - ExecARInsertTriggers(estate, resultRelInfo, - slots[i], recheckIndexes, - cstate->transition_capture); - list_free(recheckIndexes); - } + oldcontext = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate)); + + table_multi_insert(resultRelInfo->ri_RelationDesc, + slots, + nused, + mycid, + ti_options, + buffer->bistate); + MemoryContextSwitchTo(oldcontext); - /* - * There's no indexes, but see if we need to run AFTER ROW INSERT - * triggers anyway. - */ - else if (resultRelInfo->ri_TrigDesc != NULL && - (resultRelInfo->ri_TrigDesc->trig_insert_after_row || - resultRelInfo->ri_TrigDesc->trig_insert_new_table)) + for (i = 0; i < nused; i++) { - cstate->cur_lineno = buffer->linenos[i]; - ExecARInsertTriggers(estate, resultRelInfo, - slots[i], NIL, cstate->transition_capture); - } + /* + * If there are any indexes, update them for all the inserted tuples, + * and run AFTER ROW INSERT triggers. + */ + if (resultRelInfo->ri_NumIndices > 0) + { + List *recheckIndexes; + + cstate->cur_lineno = buffer->linenos[i]; + recheckIndexes = + ExecInsertIndexTuples(buffer->slots[i], estate, false, NULL, + NIL); + ExecARInsertTriggers(estate, resultRelInfo, + slots[i], recheckIndexes, + cstate->transition_capture); + list_free(recheckIndexes); + } + + /* + * There's no indexes, but see if we need to run AFTER ROW INSERT + * triggers anyway. + */ + else if (resultRelInfo->ri_TrigDesc != NULL && + (resultRelInfo->ri_TrigDesc->trig_insert_after_row || + resultRelInfo->ri_TrigDesc->trig_insert_new_table)) + { + cstate->cur_lineno = buffer->linenos[i]; + ExecARInsertTriggers(estate, resultRelInfo, + slots[i], NIL, cstate->transition_capture); + } - ExecClearTuple(slots[i]); + ExecClearTuple(slots[i]); + } } /* Mark that all slots are free */ @@ -2806,11 +2853,6 @@ CopyFrom(CopyState cstate) mtstate->operation = CMD_INSERT; mtstate->resultRelInfo = estate->es_result_relations; - if (resultRelInfo->ri_FdwRoutine != NULL && - resultRelInfo->ri_FdwRoutine->BeginForeignInsert != NULL) - resultRelInfo->ri_FdwRoutine->BeginForeignInsert(mtstate, - resultRelInfo); - /* Prepare to catch AFTER triggers. */ AfterTriggerBeginQuery(); @@ -2869,14 +2911,13 @@ CopyFrom(CopyState cstate) */ insertMethod = CIM_SINGLE; } - else if (resultRelInfo->ri_FdwRoutine != NULL || - cstate->volatile_defexprs) + else if (cstate->volatile_defexprs || list_length(cstate->attnumlist) == 0) { /* - * Can't support multi-inserts to foreign tables or if there are any - * volatile default expressions in the table. Similarly to the - * trigger case above, such expressions may query the table we're - * inserting into. + * Can't support bufferization of copy into foreign tables without any + * defined columns or if there are any volatile default expressions in the + * table. Similarly to the trigger case above, such expressions may query + * the table we're inserting into. * * Note: It does not matter if any partitions have any volatile * default expressions as we use the defaults from the target of the @@ -2916,6 +2957,24 @@ CopyFrom(CopyState cstate) estate, mycid, ti_options); } + if (insertMethod != CIM_SINGLE) + resultRelInfo->ri_usesBulkModify = true; + + /* + * Init COPY into foreign table. Initialization of copying into foreign + * partitions will be done later. + */ + if (target_resultRelInfo->ri_FdwRoutine != NULL) + { + if (target_resultRelInfo->ri_usesBulkModify && + target_resultRelInfo->ri_FdwRoutine->BeginForeignCopyIn != NULL) + target_resultRelInfo->ri_FdwRoutine->BeginForeignCopyIn(mtstate, + resultRelInfo); + else if (target_resultRelInfo->ri_FdwRoutine->BeginForeignInsert != NULL) + target_resultRelInfo->ri_FdwRoutine->BeginForeignInsert(mtstate, + resultRelInfo); + } + /* * If not using batch mode (which allocates slots as needed) set up a * tuple slot too. When inserting into a partitioned table, we also need @@ -3039,7 +3098,7 @@ CopyFrom(CopyState cstate) leafpart_use_multi_insert = insertMethod == CIM_MULTI_CONDITIONAL && !has_before_insert_row_trig && !has_instead_insert_row_trig && - resultRelInfo->ri_FdwRoutine == NULL; + (resultRelInfo->ri_FdwRoutine == NULL || resultRelInfo->ri_usesBulkModify); /* Set the multi-insert buffer to use for this partition. */ if (leafpart_use_multi_insert) @@ -3298,10 +3357,17 @@ CopyFrom(CopyState cstate) ExecResetTupleTable(estate->es_tupleTable, false); /* Allow the FDW to shut down */ - if (target_resultRelInfo->ri_FdwRoutine != NULL && - target_resultRelInfo->ri_FdwRoutine->EndForeignInsert != NULL) - target_resultRelInfo->ri_FdwRoutine->EndForeignInsert(estate, - target_resultRelInfo); + if (target_resultRelInfo->ri_FdwRoutine != NULL) + { + if (target_resultRelInfo->ri_usesBulkModify && + target_resultRelInfo->ri_FdwRoutine->EndForeignCopyIn != NULL) + target_resultRelInfo->ri_FdwRoutine->EndForeignCopyIn(estate, + target_resultRelInfo); + else if (target_resultRelInfo->ri_FdwRoutine->EndForeignInsert != NULL) + target_resultRelInfo->ri_FdwRoutine->EndForeignInsert(estate, + target_resultRelInfo); + target_resultRelInfo->ri_usesBulkModify = false; + } /* Tear down the multi-insert buffer data */ if (insertMethod != CIM_SINGLE) @@ -3354,7 +3420,8 @@ BeginCopyFrom(ParseState *pstate, MemoryContext oldcontext; bool volatile_defexprs; - cstate = BeginCopy(pstate, true, rel, NULL, InvalidOid, attnamelist, options); + cstate = BeginCopy(pstate, true, rel, NULL, NULL, InvalidOid, attnamelist, + options); oldcontext = MemoryContextSwitchTo(cstate->copycontext); /* Initialize state variables */ diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index 4fdffad6f3..b8b09d528e 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -1345,6 +1345,7 @@ InitResultRelInfo(ResultRelInfo *resultRelInfo, resultRelInfo->ri_PartitionRoot = partition_root; resultRelInfo->ri_PartitionInfo = NULL; /* may be set later */ resultRelInfo->ri_CopyMultiInsertBuffer = NULL; + resultRelInfo->ri_usesBulkModify = false; } /* diff --git a/src/backend/executor/execPartition.c b/src/backend/executor/execPartition.c index fb6ce49056..1344434cf0 100644 --- a/src/backend/executor/execPartition.c +++ b/src/backend/executor/execPartition.c @@ -526,6 +526,11 @@ ExecInitPartitionInfo(ModifyTableState *mtstate, EState *estate, rootrel, estate->es_instrument); + if (rootResultRelInfo->ri_usesBulkModify && + leaf_part_rri->ri_FdwRoutine != NULL && + leaf_part_rri->ri_FdwRoutine->BeginForeignCopyIn != NULL) + leaf_part_rri->ri_usesBulkModify = true; + /* * Verify result relation is a valid target for an INSERT. An UPDATE of a * partition-key becomes a DELETE+INSERT operation, so this check is still @@ -937,9 +942,16 @@ ExecInitRoutingInfo(ModifyTableState *mtstate, * If the partition is a foreign table, let the FDW init itself for * routing tuples to the partition. */ - if (partRelInfo->ri_FdwRoutine != NULL && - partRelInfo->ri_FdwRoutine->BeginForeignInsert != NULL) - partRelInfo->ri_FdwRoutine->BeginForeignInsert(mtstate, partRelInfo); + if (partRelInfo->ri_FdwRoutine != NULL) + { + if (partRelInfo->ri_usesBulkModify) + { + Assert(partRelInfo->ri_FdwRoutine->BeginForeignCopyIn != NULL); + partRelInfo->ri_FdwRoutine->BeginForeignCopyIn(mtstate, partRelInfo); + } + else if (partRelInfo->ri_FdwRoutine->BeginForeignInsert != NULL) + partRelInfo->ri_FdwRoutine->BeginForeignInsert(mtstate, partRelInfo); + } partRelInfo->ri_PartitionInfo = partrouteinfo; partRelInfo->ri_CopyMultiInsertBuffer = NULL; @@ -1121,10 +1133,18 @@ ExecCleanupTupleRouting(ModifyTableState *mtstate, ResultRelInfo *resultRelInfo = proute->partitions[i]; /* Allow any FDWs to shut down */ - if (resultRelInfo->ri_FdwRoutine != NULL && - resultRelInfo->ri_FdwRoutine->EndForeignInsert != NULL) - resultRelInfo->ri_FdwRoutine->EndForeignInsert(mtstate->ps.state, - resultRelInfo); + if (resultRelInfo->ri_FdwRoutine != NULL) + { + if (resultRelInfo->ri_usesBulkModify) + { + Assert(resultRelInfo->ri_FdwRoutine->EndForeignCopyIn != NULL); + resultRelInfo->ri_FdwRoutine->EndForeignCopyIn(mtstate->ps.state, + resultRelInfo); + } + else if (resultRelInfo->ri_FdwRoutine->EndForeignInsert != NULL) + resultRelInfo->ri_FdwRoutine->EndForeignInsert(mtstate->ps.state, + resultRelInfo); + } /* * Check if this result rel is one belonging to the node's subplans, diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h index c639833565..08309149ea 100644 --- a/src/include/commands/copy.h +++ b/src/include/commands/copy.h @@ -22,6 +22,7 @@ /* CopyStateData is private in commands/copy.c */ typedef struct CopyStateData *CopyState; typedef int (*copy_data_source_cb) (void *outbuf, int minread, int maxread); +typedef void (*copy_data_dest_cb) (void *outbuf, int len); extern void DoCopy(ParseState *state, const CopyStmt *stmt, int stmt_location, int stmt_len, @@ -39,6 +40,16 @@ extern void CopyFromErrorCallback(void *arg); extern uint64 CopyFrom(CopyState cstate); +extern CopyState BeginCopyTo(ParseState *pstate, Relation rel, + TupleDesc tupDesc, RawStmt *query, + Oid queryRelId, const char *filename, bool is_program, + copy_data_dest_cb data_dest_cb, List *attnamelist, + List *options); +extern void EndCopyTo(CopyState cstate); +extern void CopyOneRowTo(CopyState cstate, TupleTableSlot *slot); +extern void CopyToStart(CopyState cstate); +extern void CopyToFinish(CopyState cstate); + extern DestReceiver *CreateCopyDestReceiver(void); #endif /* COPY_H */ diff --git a/src/include/foreign/fdwapi.h b/src/include/foreign/fdwapi.h index 95556dfb15..11ea451fe4 100644 --- a/src/include/foreign/fdwapi.h +++ b/src/include/foreign/fdwapi.h @@ -104,6 +104,16 @@ typedef void (*BeginForeignInsert_function) (ModifyTableState *mtstate, typedef void (*EndForeignInsert_function) (EState *estate, ResultRelInfo *rinfo); +typedef void (*BeginForeignCopyIn_function) (ModifyTableState *mtstate, + ResultRelInfo *rinfo); + +typedef void (*EndForeignCopyIn_function) (EState *estate, + ResultRelInfo *rinfo); + +typedef void (*ExecForeignCopyIn_function) (ResultRelInfo *rinfo, + TupleTableSlot **slots, + int nslots); + typedef int (*IsForeignRelUpdatable_function) (Relation rel); typedef bool (*PlanDirectModify_function) (PlannerInfo *root, @@ -220,6 +230,11 @@ typedef struct FdwRoutine IterateDirectModify_function IterateDirectModify; EndDirectModify_function EndDirectModify; + /* COPY a bulk of tuples into a foreign relation */ + BeginForeignCopyIn_function BeginForeignCopyIn; + EndForeignCopyIn_function EndForeignCopyIn; + ExecForeignCopyIn_function ExecForeignCopyIn; + /* Functions for SELECT FOR UPDATE/SHARE row locking */ GetForeignRowMarkType_function GetForeignRowMarkType; RefetchForeignRow_function RefetchForeignRow; diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 6f96b31fb4..de326035da 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -491,6 +491,14 @@ typedef struct ResultRelInfo /* For use by copy.c when performing multi-inserts */ struct CopyMultiInsertBuffer *ri_CopyMultiInsertBuffer; + + /* + * For use by copy.c: + * for partitioned relation "true" means that child relations are allowed for + * using bulk modify operations; for foreign relation (or foreign partition + * of) "true" value means that modify operations must use bulk FDW API. + */ + bool ri_usesBulkModify; } ResultRelInfo; /* ---------------- -- 2.25.1
