v8-0005-Tests-for-parallel-copy.patch
text/x-patch
Filename: v8-0005-Tests-for-parallel-copy.patch
Type: text/x-patch
Part: 4
Message:
Re: Parallel copy
Patch
Same data as JSON:
GET /api/v1/attachments/:id/patch
the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes.
API reference →
Format: format-patch
Series: patch v8-0005
Subject: Tests for parallel copy.
| File | + | − |
|---|---|---|
| contrib/postgres_fdw/expected/postgres_fdw.out | 49 | 0 |
| contrib/postgres_fdw/sql/postgres_fdw.sql | 52 | 0 |
| src/backend/commands/copyparallel.c | 346 | 23 |
| src/test/regress/expected/copy2.out | 322 | 4 |
| src/test/regress/input/copy.source | 31 | 0 |
| src/test/regress/output/copy.source | 27 | 0 |
| src/test/regress/sql/copy2.sql | 364 | 4 |
From 3d72c381b024c8eb93324e250c1e628aa78965d0 Mon Sep 17 00:00:00 2001
From: Bharath Rupireddy <bharath.rupireddy@enterprisedb.com>
Date: Tue, 13 Oct 2020 14:23:10 +0530
Subject: [PATCH v8 5/6] Tests for parallel copy.
This patch has the tests for parallel copy:
---
contrib/postgres_fdw/expected/postgres_fdw.out | 49 ++++
contrib/postgres_fdw/sql/postgres_fdw.sql | 52 ++++
src/backend/commands/copyparallel.c | 369 +++++++++++++++++++++++--
src/test/regress/expected/copy2.out | 326 +++++++++++++++++++++-
src/test/regress/input/copy.source | 31 +++
src/test/regress/output/copy.source | 27 ++
src/test/regress/sql/copy2.sql | 368 +++++++++++++++++++++++-
7 files changed, 1191 insertions(+), 31 deletions(-)
diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out
index 2d88d06..474c5e7 100644
--- a/contrib/postgres_fdw/expected/postgres_fdw.out
+++ b/contrib/postgres_fdw/expected/postgres_fdw.out
@@ -9033,5 +9033,54 @@ SELECT 1 FROM ft1 LIMIT 1; -- should fail
ERROR: 08006
\set VERBOSITY default
COMMIT;
+-- parallel copy related tests.
+CREATE TABLE test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) ;
+CREATE FOREIGN TABLE test_parallel_copy_ft (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) SERVER loopback OPTIONS (table_name 'test_parallel_copy') ;
+-- parallel copy into foreign table, parallelism must not be picked up.
+COPY test_parallel_copy_ft FROM stdin WITH (PARALLEL 1);
+SELECT count(*) FROM test_parallel_copy_ft;
+ count
+-------
+ 2
+(1 row)
+
+-- parallel copy into a table with foreign partition.
+CREATE TABLE part_test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) PARTITION BY LIST (b);
+CREATE FOREIGN TABLE part_test_parallel_copy_a1 (c TEXT, b INT, a INT, e TEXT, d TEXT) SERVER loopback;
+CREATE TABLE part_test_parallel_copy_a2 (a INT, c TEXT, b INT, d TEXT, e TEXT);
+ALTER TABLE part_test_parallel_copy ATTACH PARTITION part_test_parallel_copy_a1 FOR VALUES IN(1);
+ALTER TABLE part_test_parallel_copy ATTACH PARTITION part_test_parallel_copy_a2 FOR VALUES IN(2);
+COPY part_test_parallel_copy FROM stdin WITH (PARALLEL 1);
+ERROR: cannot perform PARALLEL COPY if partition has BEFORE/INSTEAD OF triggers, or if the partition is foreign partition
+HINT: Try COPY without PARALLEL option
+CONTEXT: COPY part_test_parallel_copy, line 1: "1 1 test_c1 test_d1 test_e1"
+parallel worker
+SELECT count(*) FROM part_test_parallel_copy WHERE b = 2;
+ count
+-------
+ 0
+(1 row)
+
-- Clean up
DROP PROCEDURE terminate_backend_and_wait(text);
+DROP FOREIGN TABLE test_parallel_copy_ft;
+DROP TABLE test_parallel_copy;
+DROP TABLE part_test_parallel_copy;
diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql
index 7581c54..635fcc2 100644
--- a/contrib/postgres_fdw/sql/postgres_fdw.sql
+++ b/contrib/postgres_fdw/sql/postgres_fdw.sql
@@ -2695,5 +2695,57 @@ SELECT 1 FROM ft1 LIMIT 1; -- should fail
\set VERBOSITY default
COMMIT;
+-- parallel copy related tests.
+CREATE TABLE test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) ;
+
+CREATE FOREIGN TABLE test_parallel_copy_ft (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) SERVER loopback OPTIONS (table_name 'test_parallel_copy') ;
+
+-- parallel copy into foreign table, parallelism must not be picked up.
+COPY test_parallel_copy_ft FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+SELECT count(*) FROM test_parallel_copy_ft;
+
+-- parallel copy into a table with foreign partition.
+CREATE TABLE part_test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) PARTITION BY LIST (b);
+
+CREATE FOREIGN TABLE part_test_parallel_copy_a1 (c TEXT, b INT, a INT, e TEXT, d TEXT) SERVER loopback;
+
+CREATE TABLE part_test_parallel_copy_a2 (a INT, c TEXT, b INT, d TEXT, e TEXT);
+
+ALTER TABLE part_test_parallel_copy ATTACH PARTITION part_test_parallel_copy_a1 FOR VALUES IN(1);
+
+ALTER TABLE part_test_parallel_copy ATTACH PARTITION part_test_parallel_copy_a2 FOR VALUES IN(2);
+
+COPY part_test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+SELECT count(*) FROM part_test_parallel_copy WHERE b = 2;
+
-- Clean up
DROP PROCEDURE terminate_backend_and_wait(text);
+DROP FOREIGN TABLE test_parallel_copy_ft;
+DROP TABLE test_parallel_copy;
+DROP TABLE part_test_parallel_copy;
diff --git a/src/backend/commands/copyparallel.c b/src/backend/commands/copyparallel.c
index 436df40..add4dbc 100644
--- a/src/backend/commands/copyparallel.c
+++ b/src/backend/commands/copyparallel.c
@@ -102,6 +102,7 @@ SerializeParallelCopyState(ParallelContext *pcxt, CopyState cstate,
shared_cstate.convert_selectively = cstate->convert_selectively;
shared_cstate.num_defaults = cstate->num_defaults;
shared_cstate.relid = cstate->pcdata->relid;
+ shared_cstate.binary = cstate->binary;
memcpy(shmptr, (char *) &shared_cstate, sizeof(SerializedParallelCopyState));
copiedsize = sizeof(SerializedParallelCopyState);
@@ -226,6 +227,7 @@ RestoreParallelCopyState(shm_toc *toc, CopyState cstate, List **attlist)
cstate->convert_selectively = shared_cstate.convert_selectively;
cstate->num_defaults = shared_cstate.num_defaults;
cstate->pcdata->relid = shared_cstate.relid;
+ cstate->binary = shared_cstate.binary;
cstate->null_print = CopyStringFromSharedMemory(shared_str_val + copiedsize,
&copiedsize);
@@ -438,10 +440,6 @@ CheckExprParallelSafety(CopyState cstate)
bool
IsParallelCopyAllowed(CopyState cstate)
{
- /* Parallel copy not allowed for binary option. */
- if (cstate->binary)
- return false;
-
/*
* Check if copy is into foreign table. We can not allow parallelism in
* this case because each worker needs to establish FDW connection and
@@ -656,6 +654,7 @@ InitializeParallelCopyInfo(CopyState cstate, List *attnamelist)
cstate->cur_lineno = 0;
cstate->cur_attname = NULL;
cstate->cur_attval = NULL;
+ cstate->pcdata->curr_data_block = NULL;
/* Set up variables to avoid per-attribute overhead. */
initStringInfo(&cstate->attribute_buf);
@@ -878,7 +877,11 @@ return_line:
/* Mark that encoding conversion hasn't occurred yet. */
cstate->line_buf_converted = false;
- ConvertToServerEncoding(cstate);
+
+ /* For binary format data, we don't need conversion. */
+ if (!cstate->binary)
+ ConvertToServerEncoding(cstate);
+
pcdata->worker_line_buf_pos++;
return false;
}
@@ -1034,33 +1037,70 @@ ParallelCopyFrom(CopyState cstate)
/* Execute the before statement triggers from the leader */
ExecBeforeStmtTrigger(cstate);
- /* On input just throw the header line away. */
- if (cstate->cur_lineno == 0 && cstate->header_line)
+ if (!cstate->binary)
{
- cstate->cur_lineno++;
- if (CopyReadLine(cstate))
+ /* On input just throw the header line away. */
+ if (cstate->cur_lineno == 0 && cstate->header_line)
{
- pcshared_info->is_read_in_progress = false;
- return; /* done */
+ cstate->cur_lineno++;
+ if (CopyReadLine(cstate))
+ {
+ pcshared_info->is_read_in_progress = false;
+ return; /* done */
+ }
}
- }
- for (;;)
- {
- bool done;
+ for (;;)
+ {
+ bool done;
- cstate->cur_lineno++;
+ cstate->cur_lineno++;
- /* Actually read the line into memory here. */
- done = CopyReadLine(cstate);
+ /* Actually read the line into memory here. */
+ done = CopyReadLine(cstate);
+ /*
+ * EOF at start of line means we're done. If we see EOF after
+ * some characters, we act as though it was newline followed by
+ * EOF, ie, process the line and then exit loop on next iteration.
+ */
+ if (done && cstate->line_buf.len == 0)
+ break;
+ }
+ }
+ else
+ {
/*
- * EOF at start of line means we're done. If we see EOF after some
- * characters, we act as though it was newline followed by EOF, ie,
- * process the line and then exit loop on next iteration.
+ * Binary Format Files. In parallel copy leader, fill in the error
+ * context information here, in case any failures while determining
+ * tuple offsets, leader would throw the errors with proper context.
*/
- if (done && cstate->line_buf.len == 0)
- break;
+ ErrorContextCallback errcallback;
+
+ errcallback.callback = CopyFromErrorCallback;
+ errcallback.arg = (void *) cstate;
+ errcallback.previous = error_context_stack;
+ error_context_stack = &errcallback;
+ cstate->pcdata->curr_data_block = NULL;
+ cstate->raw_buf_index = 0;
+ pcshared_info->populated = 0;
+ cstate->cur_lineno = 0;
+ cstate->max_fields = list_length(cstate->attnumlist);
+
+ for (;;)
+ {
+ bool eof = false;
+
+ cstate->cur_lineno++;
+
+ eof = CopyReadBinaryTupleLeader(cstate);
+
+ if (eof)
+ break;
+ }
+
+ /* Reset the error context. */
+ error_context_stack = errcallback.previous;
}
/*
@@ -1075,6 +1115,289 @@ ParallelCopyFrom(CopyState cstate)
}
/*
+ * CopyReadBinaryGetDataBlock
+ *
+ * Gets a new block, updates the current offset, calculates the skip bytes.
+ */
+void
+CopyReadBinaryGetDataBlock(CopyState cstate, FieldInfoType field_info)
+{
+ ParallelCopyDataBlock *data_block = NULL;
+ ParallelCopyDataBlock *curr_data_block = cstate->pcdata->curr_data_block;
+ ParallelCopyShmInfo *pcshared_info = cstate->pcdata->pcshared_info;
+ uint8 move_bytes = 0;
+ uint32 block_pos;
+ uint32 prev_block_pos;
+ int read_bytes = 0;
+
+ prev_block_pos = pcshared_info->cur_block_pos;
+
+ block_pos = WaitGetFreeCopyBlock(pcshared_info);
+
+ if (field_info == FIELD_SIZE || field_info == FIELD_COUNT)
+ move_bytes = (DATA_BLOCK_SIZE - cstate->raw_buf_index);
+
+ if (curr_data_block != NULL)
+ curr_data_block->skip_bytes = move_bytes;
+
+ data_block = &pcshared_info->data_blocks[block_pos];
+
+ if (move_bytes > 0 && curr_data_block != NULL)
+ memmove(&data_block->data[0], &curr_data_block->data[cstate->raw_buf_index], move_bytes);
+
+ elog(DEBUG1, "LEADER - field info %d is spread across data blocks - moved %d bytes from current block %u to %u block",
+ field_info, move_bytes, prev_block_pos, block_pos);
+
+ read_bytes = CopyGetData(cstate, &data_block->data[move_bytes], 1, (DATA_BLOCK_SIZE - move_bytes));
+
+ if (field_info == FIELD_NONE && cstate->reached_eof)
+ return;
+
+ if (cstate->reached_eof)
+ EOF_ERROR;
+
+ elog(DEBUG1, "LEADER - bytes read from file %d", read_bytes);
+
+ if (field_info == FIELD_SIZE || field_info == FIELD_DATA)
+ {
+ ParallelCopyDataBlock *prev_data_block = NULL;
+
+ prev_data_block = curr_data_block;
+ prev_data_block->following_block = block_pos;
+
+ if (prev_data_block->curr_blk_completed == false)
+ prev_data_block->curr_blk_completed = true;
+
+ pg_atomic_add_fetch_u32(&prev_data_block->unprocessed_line_parts, 1);
+ }
+
+ cstate->pcdata->curr_data_block = data_block;
+ cstate->raw_buf_index = 0;
+}
+
+/*
+ * CopyReadBinaryTupleLeader
+ *
+ * Leader reads data from binary formatted file to data blocks and identifies
+ * tuple boundaries/offsets so that workers can work on the data blocks data.
+ */
+bool
+CopyReadBinaryTupleLeader(CopyState cstate)
+{
+ ParallelCopyShmInfo *pcshared_info = cstate->pcdata->pcshared_info;
+ int16 fld_count;
+ uint32 line_size = 0;
+ uint32 start_block_pos;
+ uint32 start_offset;
+
+ if (cstate->pcdata->curr_data_block == NULL)
+ {
+ CopyReadBinaryGetDataBlock(cstate, FIELD_NONE);
+
+ /*
+ * no data is read from file here. one possibility to be here could be
+ * that the binary file just has a valid signature but nothing else.
+ */
+ if (cstate->reached_eof)
+ return true;
+ }
+
+ if ((cstate->raw_buf_index + sizeof(fld_count)) >= DATA_BLOCK_SIZE)
+ CopyReadBinaryGetDataBlock(cstate, FIELD_COUNT);
+
+ memcpy(&fld_count, &cstate->pcdata->curr_data_block->data[cstate->raw_buf_index], sizeof(fld_count));
+ fld_count = (int16) pg_ntoh16(fld_count);
+
+ CHECK_FIELD_COUNT;
+
+ start_offset = cstate->raw_buf_index;
+ cstate->raw_buf_index += sizeof(fld_count);
+ line_size += sizeof(fld_count);
+ start_block_pos = pcshared_info->cur_block_pos;
+
+ CopyReadBinaryFindTupleSize(cstate, &line_size);
+
+ pg_atomic_add_fetch_u32(&cstate->pcdata->curr_data_block->unprocessed_line_parts, 1);
+
+ if (line_size > 0)
+ (void) UpdateSharedLineInfo(cstate, start_block_pos, start_offset,
+ line_size, LINE_LEADER_POPULATED, -1);
+
+ return false;
+}
+
+/*
+ * CopyReadBinaryFindTupleSize
+ *
+ * Leader identifies boundaries/offsets for each attribute/column and finally
+ * results in the tuple/row size. It moves on to next data block if the
+ * attribute/column is spread across data blocks.
+ */
+void
+CopyReadBinaryFindTupleSize(CopyState cstate, uint32 *line_size)
+{
+ int32 fld_size;
+ ListCell *cur;
+ TupleDesc tup_desc = RelationGetDescr(cstate->rel);
+
+ foreach(cur, cstate->attnumlist)
+ {
+ int att_num = lfirst_int(cur);
+ Form_pg_attribute att = TupleDescAttr(tup_desc, (att_num - 1));
+
+ cstate->cur_attname = NameStr(att->attname);
+ fld_size = 0;
+
+ if ((cstate->raw_buf_index + sizeof(fld_size)) >= DATA_BLOCK_SIZE)
+ CopyReadBinaryGetDataBlock(cstate, FIELD_SIZE);
+
+ memcpy(&fld_size, &cstate->pcdata->curr_data_block->data[cstate->raw_buf_index], sizeof(fld_size));
+ cstate->raw_buf_index += sizeof(fld_size);
+ *line_size += sizeof(fld_size);
+ fld_size = (int32) pg_ntoh32(fld_size);
+
+ /* fld_size -1 represents the null value for the field. */
+ if (fld_size == -1)
+ continue;
+
+ CHECK_FIELD_SIZE(fld_size);
+
+ *line_size += fld_size;
+
+ if ((DATA_BLOCK_SIZE - cstate->raw_buf_index) >= fld_size)
+ {
+ cstate->raw_buf_index += fld_size;
+ elog(DEBUG1, "LEADER - tuple lies in he same data block");
+ }
+ else
+ {
+ int32 required_blks = 0;
+ int32 curr_blk_bytes = (DATA_BLOCK_SIZE - cstate->raw_buf_index);
+ int i = 0;
+
+ GET_REQUIRED_BLOCKS(required_blks, fld_size, curr_blk_bytes);
+
+ i = required_blks;
+
+ while (i > 0)
+ {
+ CopyReadBinaryGetDataBlock(cstate, FIELD_DATA);
+ i--;
+ }
+
+ GET_RAW_BUF_INDEX(cstate->raw_buf_index, fld_size, required_blks, curr_blk_bytes);
+
+ /*
+ * raw_buf_index should never cross data block size, as the
+ * required number of data blocks would have been obtained in the
+ * above while loop.
+ */
+ Assert(cstate->raw_buf_index <= DATA_BLOCK_SIZE);
+ }
+ cstate->cur_attname = NULL;
+ }
+}
+
+/*
+ * CopyReadBinaryTupleWorker
+ *
+ * Each worker reads data from data blocks caches the tuple data into local
+ * memory.
+ */
+bool
+CopyReadBinaryTupleWorker(CopyState cstate, Datum *values, bool *nulls)
+{
+ int16 fld_count;
+ ListCell *cur;
+ FmgrInfo *in_functions = cstate->in_functions;
+ Oid *typioparams = cstate->typioparams;
+ TupleDesc tup_desc = RelationGetDescr(cstate->rel);
+ bool done = false;
+
+ done = GetWorkerLine(cstate);
+ cstate->raw_buf_index = 0;
+
+ if (done && cstate->line_buf.len == 0)
+ return true;
+
+ memcpy(&fld_count, &cstate->line_buf.data[cstate->raw_buf_index], sizeof(fld_count));
+ fld_count = (int16) pg_ntoh16(fld_count);
+
+ CHECK_FIELD_COUNT;
+
+ cstate->raw_buf_index += sizeof(fld_count);
+
+ foreach(cur, cstate->attnumlist)
+ {
+ int att_num = lfirst_int(cur);
+ int m = att_num - 1;
+ Form_pg_attribute att = TupleDescAttr(tup_desc, m);
+
+ cstate->cur_attname = NameStr(att->attname);
+
+ values[m] = CopyReadBinaryAttributeWorker(cstate,
+ &in_functions[m],
+ typioparams[m],
+ att->atttypmod,
+ &nulls[m]);
+ cstate->cur_attname = NULL;
+ }
+
+ return false;
+}
+
+/*
+ * CopyReadBinaryAttributeWorker
+ *
+ * Worker identifies and converts each attribute/column data from binary to
+ * the data type of attribute/column.
+ */
+Datum
+CopyReadBinaryAttributeWorker(CopyState cstate, FmgrInfo *flinfo,
+ Oid typioparam, int32 typmod, bool *isnull)
+{
+ int32 fld_size;
+ Datum result;
+
+ memcpy(&fld_size, &cstate->line_buf.data[cstate->raw_buf_index], sizeof(fld_size));
+ cstate->raw_buf_index += sizeof(fld_size);
+ fld_size = (int32) pg_ntoh32(fld_size);
+
+ /* fld_size -1 represents the null value for the field. */
+ if (fld_size == -1)
+ {
+ *isnull = true;
+ return ReceiveFunctionCall(flinfo, NULL, typioparam, typmod);
+ }
+
+ CHECK_FIELD_SIZE(fld_size);
+
+ /* Reset attribute_buf to empty, and load raw data in it */
+ resetStringInfo(&cstate->attribute_buf);
+
+ enlargeStringInfo(&cstate->attribute_buf, fld_size);
+
+ memcpy(&cstate->attribute_buf.data[0], &cstate->line_buf.data[cstate->raw_buf_index], fld_size);
+ cstate->raw_buf_index += fld_size;
+
+ cstate->attribute_buf.len = fld_size;
+ cstate->attribute_buf.data[fld_size] = '\0';
+
+ /* Call the column type's binary input converter */
+ result = ReceiveFunctionCall(flinfo, &cstate->attribute_buf,
+ typioparam, typmod);
+
+ /* Trouble if it didn't eat the whole buffer */
+ if (cstate->attribute_buf.cursor != cstate->attribute_buf.len)
+ ereport(ERROR,
+ (errcode(ERRCODE_INVALID_BINARY_REPRESENTATION),
+ errmsg("incorrect binary data format")));
+
+ *isnull = false;
+ return result;
+}
+
+/*
* GetLinePosition
*
* Return the line position once the leader has populated the data.
diff --git a/src/test/regress/expected/copy2.out b/src/test/regress/expected/copy2.out
index c64f071..08ce743 100644
--- a/src/test/regress/expected/copy2.out
+++ b/src/test/regress/expected/copy2.out
@@ -301,18 +301,32 @@ It is "perfect".|
"It is ""perfect""."," "
"",
--test that we read consecutive LFs properly
-CREATE TEMP TABLE testnl (a int, b text, c int);
+CREATE TABLE testnl (a int, b text, c int);
COPY testnl FROM stdin CSV;
+COPY testnl FROM stdin WITH (FORMAT 'csv', PARALLEL 1);
+SELECT * FROM testnl;
+ a | b | c
+---+----------------------+---
+ 1 | a field with two LFs+| 2
+ | +|
+ | inside |
+ 1 | a field with two LFs+| 2
+ | +|
+ | inside |
+(2 rows)
+
-- test end of copy marker
-CREATE TEMP TABLE testeoc (a text);
+CREATE TABLE testeoc (a text);
COPY testeoc FROM stdin CSV;
+TRUNCATE testeoc;
+COPY testeoc FROM stdin WITH (FORMAT 'csv', PARALLEL 1);
COPY testeoc TO stdout CSV;
a\.
\.b
c\.d
"\."
-- test handling of nonstandard null marker that violates escaping rules
-CREATE TEMP TABLE testnull(a int, b text);
+CREATE TABLE testnull(a int, b text);
INSERT INTO testnull VALUES (1, E'\\0'), (NULL, NULL);
COPY testnull TO stdout WITH NULL AS E'\\0';
1 \\0
@@ -327,6 +341,15 @@ SELECT * FROM testnull;
|
(4 rows)
+TRUNCATE testnull;
+COPY testnull FROM stdin WITH (NULL E'\\0', PARALLEL 1);
+SELECT * FROM testnull;
+ a | b
+----+----
+ 42 | \0
+ |
+(2 rows)
+
BEGIN;
CREATE TABLE vistest (LIKE testeoc);
COPY vistest FROM stdin CSV;
@@ -396,6 +419,34 @@ SELECT * FROM vistest;
BEGIN;
TRUNCATE vistest;
+COPY vistest FROM stdin WITH (FORMAT 'csv', FREEZE, PARALLEL 1);
+SELECT * FROM vistest;
+ a
+----
+ a2
+ b
+(2 rows)
+
+SAVEPOINT s1;
+TRUNCATE vistest;
+COPY vistest FROM stdin WITH (FORMAT 'csv', FREEZE, PARALLEL 1);
+SELECT * FROM vistest;
+ a
+----
+ d2
+ e
+(2 rows)
+
+COMMIT;
+SELECT * FROM vistest;
+ a
+----
+ d2
+ e
+(2 rows)
+
+BEGIN;
+TRUNCATE vistest;
COPY vistest FROM stdin CSV FREEZE;
SELECT * FROM vistest;
a
@@ -456,7 +507,7 @@ SELECT * FROM vistest;
(2 rows)
-- Test FORCE_NOT_NULL and FORCE_NULL options
-CREATE TEMP TABLE forcetest (
+CREATE TABLE forcetest (
a INT NOT NULL,
b TEXT NOT NULL,
c TEXT,
@@ -467,6 +518,8 @@ CREATE TEMP TABLE forcetest (
-- should succeed with no effect ("b" remains an empty string, "c" remains NULL)
BEGIN;
COPY forcetest (a, b, c) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(b), FORCE_NULL(c));
+TRUNCATE forcetest;
+COPY forcetest (a, b, c) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(b), FORCE_NULL(c), PARALLEL 1);
COMMIT;
SELECT b, c FROM forcetest WHERE a = 1;
b | c
@@ -477,6 +530,8 @@ SELECT b, c FROM forcetest WHERE a = 1;
-- should succeed, FORCE_NULL and FORCE_NOT_NULL can be both specified
BEGIN;
COPY forcetest (a, b, c, d) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(c,d), FORCE_NULL(c,d));
+TRUNCATE forcetest;
+COPY forcetest (a, b, c, d) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(c,d), FORCE_NULL(c,d), PARALLEL 1);
COMMIT;
SELECT c, d FROM forcetest WHERE a = 2;
c | d
@@ -533,6 +588,31 @@ select * from check_con_tbl;
(2 rows)
+\d+ check_con_tbl
+ Table "public.check_con_tbl"
+ Column | Type | Collation | Nullable | Default | Storage | Stats target | Description
+--------+---------+-----------+----------+---------+---------+--------------+-------------
+ f1 | integer | | | | plain | |
+Check constraints:
+ "check_con_tbl_check" CHECK (check_con_function(check_con_tbl.*))
+
+truncate check_con_tbl;
+copy check_con_tbl from stdin with (parallel 1);
+NOTICE: input = {"f1":1}
+NOTICE: input = {"f1":null}
+copy check_con_tbl from stdin with (parallel 1);
+NOTICE: input = {"f1":0}
+ERROR: new row for relation "check_con_tbl" violates check constraint "check_con_tbl_check"
+DETAIL: Failing row contains (0).
+CONTEXT: COPY check_con_tbl, line 1: "0"
+parallel worker
+select * from check_con_tbl;
+ f1
+----
+ 1
+
+(2 rows)
+
-- test with RLS enabled.
CREATE ROLE regress_rls_copy_user;
CREATE ROLE regress_rls_copy_user_colperms;
@@ -647,10 +727,248 @@ SELECT * FROM instead_of_insert_tbl;
(2 rows)
COMMIT;
+-- Parallel copy tests.
+CREATE TABLE test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT not null default 'stuff',
+ d TEXT,
+ e TEXT
+) ;
+COPY test_parallel_copy (a, b, c, d, e) FROM stdin WITH (PARALLEL 1);
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1);
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1);
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1, FORMAT 'csv', HEADER);
+-- zero workers: should perform non-parallel copy
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL '0');
+ERROR: value 0 out of bounds for option "parallel"
+DETAIL: Valid values are between "1" and "1024".
+-- referencing table: should perform non-parallel copy
+CREATE TABLE test_copy_pk(c1 INT PRIMARY KEY);
+INSERT INTO test_copy_pk VALUES(10);
+CREATE TABLE test_copy_ri(c1 INT REFERENCES test_copy_pk(c1));
+COPY test_copy_ri FROM stdin WITH (FORMAT csv, DELIMITER ',', PARALLEL 1);
+-- expressions: should perform non-parallel copy
+CREATE TABLE test_copy_expr (index INT, height REAL, weight REAL);
+COPY test_copy_expr FROM STDIN WITH (FORMAT csv, DELIMITER ',', PARALLEL 1) WHERE height > random() * 65;
+-- serial data: should perform non-parallel copy
+CREATE TABLE testserial (index SERIAL, height REAL);
+COPY testserial(height) FROM STDIN WITH (FORMAT csv, DELIMITER ',', PARALLEL 1);
+-- temporary table copy: should perform non-parallel copy
+CREATE TEMPORARY TABLE temp_test(
+ a int
+) ;
+COPY temp_test (a) FROM stdin WITH (PARALLEL 1);
+-- non-existent column in column list: should fail
+COPY test_parallel_copy (xyz) FROM stdin WITH (PARALLEL 1);
+ERROR: column "xyz" of relation "test_parallel_copy" does not exist
+-- too many columns in column list: should fail
+COPY test_parallel_copy (a, b, c, d, e, d, c) FROM stdin WITH (PARALLEL 1);
+ERROR: column "d" specified more than once
+-- missing data: should fail
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+ERROR: invalid input syntax for type integer: ""
+CONTEXT: COPY test_parallel_copy, line 0, column a: ""
+parallel worker
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+ERROR: missing data for column "e"
+CONTEXT: COPY test_parallel_copy, line 1: "2000 230 23 23"
+parallel worker
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+ERROR: missing data for column "e"
+CONTEXT: COPY test_parallel_copy, line 1: "2001 231 \N \N"
+parallel worker
+-- extra data: should fail
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+ERROR: extra data after last expected column
+CONTEXT: COPY test_parallel_copy, line 1: "2002 232 40 50 60 70 80"
+parallel worker
+-- various COPY options: delimiters, oids, NULL string, encoding
+COPY test_parallel_copy (b, c, d, e) FROM stdin WITH (DELIMITER ',', null 'x', PARALLEL 1) ;
+COPY test_parallel_copy FROM stdin WITH (DELIMITER ';', NULL '', PARALLEL 1);
+COPY test_parallel_copy FROM stdin WITH (DELIMITER ':', NULL E'\\X', ENCODING 'sql_ascii', PARALLEL 1);
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a = 50004;
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a > 60003;
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE f > 60003;
+ERROR: column "f" does not exist
+LINE 1: ..._parallel_copy FROM stdin WITH (PARALLEL 1) WHERE f > 60003;
+ ^
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a = max(x.b);
+ERROR: missing FROM-clause entry for table "x"
+LINE 1: ...rallel_copy FROM stdin WITH (PARALLEL 1) WHERE a = max(x.b);
+ ^
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (SELECT 1 FROM x);
+ERROR: cannot use subquery in COPY FROM WHERE condition
+LINE 1: ...arallel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (SELECT...
+ ^
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (generate_series(1,5));
+ERROR: set-returning functions are not allowed in COPY FROM WHERE conditions
+LINE 1: ...lel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (generate_s...
+ ^
+COPY test_parallel_copy FROM stdin WITH(PARALLEL 1) WHERE a = row_number() over(b);
+ERROR: window functions are not allowed in COPY FROM WHERE conditions
+LINE 1: ...rallel_copy FROM stdin WITH(PARALLEL 1) WHERE a = row_number...
+ ^
+-- check results of copy in
+SELECT * FROM test_parallel_copy ORDER BY 1;
+ a | b | c | d | e
+-------+----+------------+---------+---------
+ 1 | 11 | test_c1 | test_d1 | test_e1
+ 2 | 12 | test_c2 | test_d2 | test_e2
+ 3000 | | c | |
+ 4000 | | C | |
+ 4001 | 1 | empty | |
+ 4002 | 2 | null | |
+ 4003 | 3 | Backslash | \ | \
+ 4004 | 4 | BackslashX | \X | \X
+ 4005 | 5 | N | N | N
+ 4006 | 6 | BackslashN | \N | \N
+ 4007 | 7 | XX | XX | XX
+ 4008 | 8 | Delimiter | : | :
+ 50004 | 25 | 35 | 45 | 55
+ 60004 | 25 | 35 | 45 | 55
+ 60005 | 26 | 36 | 46 | 56
+ | 3 | stuff | test_d3 |
+ | 4 | stuff | test_d4 |
+ | 5 | stuff | test_d5 |
+ | | , | \, | \
+ | | x | \x | \x
+ | | 45 | 80 | 90
+(21 rows)
+
+-- parallel copy test for unlogged tables. should execute in parallel worker
+CREATE UNLOGGED TABLE test_parallel_copy_unlogged(
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+);
+COPY test_parallel_copy_unlogged FROM stdin WITH (PARALLEL 1);
+SELECT count(*) FROM test_parallel_copy_unlogged;
+ count
+-------
+ 2
+(1 row)
+
+-- parallel copy test for various trigger types
+TRUNCATE test_parallel_copy;
+-- parallel safe trigger function
+CREATE OR REPLACE FUNCTION parallel_copy_trig_func() RETURNS TRIGGER
+LANGUAGE plpgsql PARALLEL SAFE AS $$
+BEGIN
+ RETURN NEW;
+END;
+$$;
+-- before insert row trigger
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- after insert row trigger
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- before insert statement trigger
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- parallelism should be picked, since the trigger function is parallel safe
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- after insert statement trigger
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- transition table is involved
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy REFERENCING NEW TABLE AS new_table
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- make trigger function parallel unsafe
+ALTER FUNCTION parallel_copy_trig_func PARALLEL UNSAFE;
+-- before statement trigger has a parallel unsafe function
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+SELECT count(*) FROM test_parallel_copy;
+ count
+-------
+ 12
+(1 row)
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+-- instead of insert trigger, no parallelism should be picked
+COPY instead_of_insert_tbl_view FROM stdin WITH(PARALLEL 1);;
+SELECT count(*) FROM instead_of_insert_tbl_view;
+ count
+-------
+ 1
+(1 row)
+
+-- parallel copy test for a partitioned table with a before insert trigger on
+-- one of the partition
+ALTER FUNCTION parallel_copy_trig_func PARALLEL SAFE;
+CREATE TABLE test_parallel_copy_part (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) PARTITION BY LIST (b);
+CREATE TABLE test_parallel_copy_part_a1 (c TEXT, b INT, a INT, e TEXT, d TEXT);
+CREATE TABLE test_parallel_copy_part_a2 (a INT, c TEXT, b INT, d TEXT, e TEXT);
+ALTER TABLE test_parallel_copy_part ATTACH PARTITION test_parallel_copy_part_a1 FOR VALUES IN(1);
+ALTER TABLE test_parallel_copy_part ATTACH PARTITION test_parallel_copy_part_a2 FOR VALUES IN(2);
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy_part_a2
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+COPY test_parallel_copy_part FROM stdin WITH (PARALLEL 1);
+ERROR: cannot perform PARALLEL COPY if partition has BEFORE/INSTEAD OF triggers, or if the partition is foreign partition
+HINT: Try COPY without PARALLEL option
+CONTEXT: COPY test_parallel_copy_part, line 2: "2 2 test_c2 test_d2 test_e2"
+parallel worker
+SELECT count(*) FROM test_parallel_copy_part;
+ count
+-------
+ 0
+(1 row)
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy_part_a2;
-- clean up
+DROP TABLE test_copy_ri;
+DROP TABLE test_copy_pk;
+DROP TABLE test_copy_expr;
+DROP TABLE testeoc;
+DROP TABLE testnl;
DROP TABLE forcetest;
+DROP TABLE test_parallel_copy;
+DROP TABLE test_parallel_copy_unlogged;
+DROP TABLE test_parallel_copy_part;
+DROP TABLE testserial;
+DROP TABLE testnull;
DROP TABLE vistest;
DROP FUNCTION truncate_in_subxact();
+DROP FUNCTION parallel_copy_trig_func();
DROP TABLE x, y;
DROP TABLE rls_t1 CASCADE;
DROP ROLE regress_rls_copy_user;
diff --git a/src/test/regress/input/copy.source b/src/test/regress/input/copy.source
index a1d529a..cb39c66 100644
--- a/src/test/regress/input/copy.source
+++ b/src/test/regress/input/copy.source
@@ -15,6 +15,13 @@ DELETE FROM onek;
COPY onek FROM '@abs_builddir@/results/onek.data';
+-- test parallel copy
+COPY tenk1 FROM '@abs_srcdir@/data/tenk.data' WITH (parallel 2);
+
+SELECT COUNT(*) FROM tenk1;
+
+TRUNCATE tenk1;
+
COPY tenk1 FROM '@abs_srcdir@/data/tenk.data';
COPY slow_emp4000 FROM '@abs_srcdir@/data/rect.data';
@@ -159,6 +166,30 @@ truncate parted_copytest;
copy parted_copytest from '@abs_builddir@/results/parted_copytest.csv';
+-- Test parallel copy from with a partitioned table.
+truncate parted_copytest;
+
+copy parted_copytest from '@abs_builddir@/results/parted_copytest.csv' with (parallel 2);
+
+-- Test parallel copy from for toast table with csv and binary format file
+create table test_parallel_copy_toast(a1 int, b1 text, c1 text default null);
+
+insert into test_parallel_copy_toast select i, (repeat(md5(i::text), 100000)) FROM generate_series(1,2) AS i;
+
+copy test_parallel_copy_toast to '@abs_builddir@/results/parallelcopytoast.csv' with(format csv);
+
+copy test_parallel_copy_toast to '@abs_builddir@/results/parallelcopytoast.dat' with(format binary);
+
+truncate test_parallel_copy_toast;
+
+copy test_parallel_copy_toast from '@abs_builddir@/results/parallelcopytoast.csv' with(format csv, parallel 2);
+
+copy test_parallel_copy_toast from '@abs_builddir@/results/parallelcopytoast.dat' with(format binary, parallel 2);
+
+select count(*) from test_parallel_copy_toast;
+
+drop table test_parallel_copy_toast;
+
-- Ensure COPY FREEZE errors for partitioned tables.
begin;
truncate parted_copytest;
diff --git a/src/test/regress/output/copy.source b/src/test/regress/output/copy.source
index 938d355..a5dca79 100644
--- a/src/test/regress/output/copy.source
+++ b/src/test/regress/output/copy.source
@@ -9,6 +9,15 @@ COPY onek FROM '@abs_srcdir@/data/onek.data';
COPY onek TO '@abs_builddir@/results/onek.data';
DELETE FROM onek;
COPY onek FROM '@abs_builddir@/results/onek.data';
+-- test parallel copy
+COPY tenk1 FROM '@abs_srcdir@/data/tenk.data' WITH (parallel 2);
+SELECT COUNT(*) FROM tenk1;
+ count
+-------
+ 10000
+(1 row)
+
+TRUNCATE tenk1;
COPY tenk1 FROM '@abs_srcdir@/data/tenk.data';
COPY slow_emp4000 FROM '@abs_srcdir@/data/rect.data';
COPY person FROM '@abs_srcdir@/data/person.data';
@@ -113,6 +122,24 @@ insert into parted_copytest select x,1,'One' from generate_series(1011,1020) x;
copy (select * from parted_copytest order by a) to '@abs_builddir@/results/parted_copytest.csv';
truncate parted_copytest;
copy parted_copytest from '@abs_builddir@/results/parted_copytest.csv';
+-- Test parallel copy from with a partitioned table.
+truncate parted_copytest;
+copy parted_copytest from '@abs_builddir@/results/parted_copytest.csv' with (parallel 2);
+-- Test parallel copy from for toast table with csv and binary format file
+create table test_parallel_copy_toast(a1 int, b1 text, c1 text default null);
+insert into test_parallel_copy_toast select i, (repeat(md5(i::text), 100000)) FROM generate_series(1,2) AS i;
+copy test_parallel_copy_toast to '@abs_builddir@/results/parallelcopytoast.csv' with(format csv);
+copy test_parallel_copy_toast to '@abs_builddir@/results/parallelcopytoast.dat' with(format binary);
+truncate test_parallel_copy_toast;
+copy test_parallel_copy_toast from '@abs_builddir@/results/parallelcopytoast.csv' with(format csv, parallel 2);
+copy test_parallel_copy_toast from '@abs_builddir@/results/parallelcopytoast.dat' with(format binary, parallel 2);
+select count(*) from test_parallel_copy_toast;
+ count
+-------
+ 4
+(1 row)
+
+drop table test_parallel_copy_toast;
-- Ensure COPY FREEZE errors for partitioned tables.
begin;
truncate parted_copytest;
diff --git a/src/test/regress/sql/copy2.sql b/src/test/regress/sql/copy2.sql
index b3c16af..b3c9af3 100644
--- a/src/test/regress/sql/copy2.sql
+++ b/src/test/regress/sql/copy2.sql
@@ -171,7 +171,7 @@ COPY y TO stdout (FORMAT CSV, FORCE_QUOTE *);
--test that we read consecutive LFs properly
-CREATE TEMP TABLE testnl (a int, b text, c int);
+CREATE TABLE testnl (a int, b text, c int);
COPY testnl FROM stdin CSV;
1,"a field with two LFs
@@ -179,8 +179,16 @@ COPY testnl FROM stdin CSV;
inside",2
\.
+COPY testnl FROM stdin WITH (FORMAT 'csv', PARALLEL 1);
+1,"a field with two LFs
+
+inside",2
+\.
+
+SELECT * FROM testnl;
+
-- test end of copy marker
-CREATE TEMP TABLE testeoc (a text);
+CREATE TABLE testeoc (a text);
COPY testeoc FROM stdin CSV;
a\.
@@ -189,11 +197,19 @@ c\.d
"\."
\.
+TRUNCATE testeoc;
+COPY testeoc FROM stdin WITH (FORMAT 'csv', PARALLEL 1);
+a\.
+\.b
+c\.d
+"\."
+\.
+
COPY testeoc TO stdout CSV;
-- test handling of nonstandard null marker that violates escaping rules
-CREATE TEMP TABLE testnull(a int, b text);
+CREATE TABLE testnull(a int, b text);
INSERT INTO testnull VALUES (1, E'\\0'), (NULL, NULL);
COPY testnull TO stdout WITH NULL AS E'\\0';
@@ -205,6 +221,14 @@ COPY testnull FROM stdin WITH NULL AS E'\\0';
SELECT * FROM testnull;
+TRUNCATE testnull;
+COPY testnull FROM stdin WITH (NULL E'\\0', PARALLEL 1);
+42 \\0
+\0 \0
+\.
+
+SELECT * FROM testnull;
+
BEGIN;
CREATE TABLE vistest (LIKE testeoc);
COPY vistest FROM stdin CSV;
@@ -249,6 +273,23 @@ SELECT * FROM vistest;
BEGIN;
TRUNCATE vistest;
+COPY vistest FROM stdin WITH (FORMAT 'csv', FREEZE, PARALLEL 1);
+a2
+b
+\.
+SELECT * FROM vistest;
+SAVEPOINT s1;
+TRUNCATE vistest;
+COPY vistest FROM stdin WITH (FORMAT 'csv', FREEZE, PARALLEL 1);
+d2
+e
+\.
+SELECT * FROM vistest;
+COMMIT;
+SELECT * FROM vistest;
+
+BEGIN;
+TRUNCATE vistest;
COPY vistest FROM stdin CSV FREEZE;
x
y
@@ -298,7 +339,7 @@ SELECT * FROM vistest;
COMMIT;
SELECT * FROM vistest;
-- Test FORCE_NOT_NULL and FORCE_NULL options
-CREATE TEMP TABLE forcetest (
+CREATE TABLE forcetest (
a INT NOT NULL,
b TEXT NOT NULL,
c TEXT,
@@ -311,6 +352,10 @@ BEGIN;
COPY forcetest (a, b, c) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(b), FORCE_NULL(c));
1,,""
\.
+TRUNCATE forcetest;
+COPY forcetest (a, b, c) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(b), FORCE_NULL(c), PARALLEL 1);
+1,,""
+\.
COMMIT;
SELECT b, c FROM forcetest WHERE a = 1;
-- should succeed, FORCE_NULL and FORCE_NOT_NULL can be both specified
@@ -318,6 +363,10 @@ BEGIN;
COPY forcetest (a, b, c, d) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(c,d), FORCE_NULL(c,d));
2,'a',,""
\.
+TRUNCATE forcetest;
+COPY forcetest (a, b, c, d) FROM STDIN WITH (FORMAT csv, FORCE_NOT_NULL(c,d), FORCE_NULL(c,d), PARALLEL 1);
+2,'a',,""
+\.
COMMIT;
SELECT c, d FROM forcetest WHERE a = 2;
-- should fail with not-null constraint violation
@@ -353,6 +402,16 @@ copy check_con_tbl from stdin;
0
\.
select * from check_con_tbl;
+\d+ check_con_tbl
+truncate check_con_tbl;
+copy check_con_tbl from stdin with (parallel 1);
+1
+\N
+\.
+copy check_con_tbl from stdin with (parallel 1);
+0
+\.
+select * from check_con_tbl;
-- test with RLS enabled.
CREATE ROLE regress_rls_copy_user;
@@ -454,10 +513,311 @@ test1
SELECT * FROM instead_of_insert_tbl;
COMMIT;
+-- Parallel copy tests.
+CREATE TABLE test_parallel_copy (
+ a INT,
+ b INT,
+ c TEXT not null default 'stuff',
+ d TEXT,
+ e TEXT
+) ;
+
+COPY test_parallel_copy (a, b, c, d, e) FROM stdin WITH (PARALLEL 1);
+1 11 test_c1 test_d1 test_e1
+2 12 test_c2 test_d2 test_e2
+\.
+
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1);
+3 test_d3
+\.
+
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1);
+4 test_d4
+5 test_d5
+\.
+
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL 1, FORMAT 'csv', HEADER);
+b d
+\.
+
+-- zero workers: should perform non-parallel copy
+COPY test_parallel_copy (b, d) FROM stdin WITH (PARALLEL '0');
+
+-- referencing table: should perform non-parallel copy
+CREATE TABLE test_copy_pk(c1 INT PRIMARY KEY);
+INSERT INTO test_copy_pk VALUES(10);
+CREATE TABLE test_copy_ri(c1 INT REFERENCES test_copy_pk(c1));
+COPY test_copy_ri FROM stdin WITH (FORMAT csv, DELIMITER ',', PARALLEL 1);
+10
+\.
+
+-- expressions: should perform non-parallel copy
+CREATE TABLE test_copy_expr (index INT, height REAL, weight REAL);
+
+COPY test_copy_expr FROM STDIN WITH (FORMAT csv, DELIMITER ',', PARALLEL 1) WHERE height > random() * 65;
+60,60,60
+\.
+
+-- serial data: should perform non-parallel copy
+CREATE TABLE testserial (index SERIAL, height REAL);
+
+COPY testserial(height) FROM STDIN WITH (FORMAT csv, DELIMITER ',', PARALLEL 1);
+60
+\.
+
+-- temporary table copy: should perform non-parallel copy
+CREATE TEMPORARY TABLE temp_test(
+ a int
+) ;
+
+COPY temp_test (a) FROM stdin WITH (PARALLEL 1);
+10
+\.
+
+-- non-existent column in column list: should fail
+COPY test_parallel_copy (xyz) FROM stdin WITH (PARALLEL 1);
+
+-- too many columns in column list: should fail
+COPY test_parallel_copy (a, b, c, d, e, d, c) FROM stdin WITH (PARALLEL 1);
+
+-- missing data: should fail
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+
+\.
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+2000 230 23 23
+\.
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+2001 231 \N \N
+\.
+
+-- extra data: should fail
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+2002 232 40 50 60 70 80
+\.
+
+-- various COPY options: delimiters, oids, NULL string, encoding
+COPY test_parallel_copy (b, c, d, e) FROM stdin WITH (DELIMITER ',', null 'x', PARALLEL 1) ;
+x,45,80,90
+x,\x,\\x,\\\x
+x,\,,\\\,,\\
+\.
+
+COPY test_parallel_copy FROM stdin WITH (DELIMITER ';', NULL '', PARALLEL 1);
+3000;;c;;
+\.
+
+COPY test_parallel_copy FROM stdin WITH (DELIMITER ':', NULL E'\\X', ENCODING 'sql_ascii', PARALLEL 1);
+4000:\X:C:\X:\X
+4001:1:empty::
+4002:2:null:\X:\X
+4003:3:Backslash:\\:\\
+4004:4:BackslashX:\\X:\\X
+4005:5:N:\N:\N
+4006:6:BackslashN:\\N:\\N
+4007:7:XX:\XX:\XX
+4008:8:Delimiter:\::\:
+\.
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a = 50004;
+50003 24 34 44 54
+50004 25 35 45 55
+50005 26 36 46 56
+\.
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a > 60003;
+60001 22 32 42 52
+60002 23 33 43 53
+60003 24 34 44 54
+60004 25 35 45 55
+60005 26 36 46 56
+\.
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE f > 60003;
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a = max(x.b);
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (SELECT 1 FROM x);
+
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1) WHERE a IN (generate_series(1,5));
+
+COPY test_parallel_copy FROM stdin WITH(PARALLEL 1) WHERE a = row_number() over(b);
+
+-- check results of copy in
+SELECT * FROM test_parallel_copy ORDER BY 1;
+
+-- parallel copy test for unlogged tables. should execute in parallel worker
+CREATE UNLOGGED TABLE test_parallel_copy_unlogged(
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+);
+
+COPY test_parallel_copy_unlogged FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+SELECT count(*) FROM test_parallel_copy_unlogged;
+
+-- parallel copy test for various trigger types
+TRUNCATE test_parallel_copy;
+
+-- parallel safe trigger function
+CREATE OR REPLACE FUNCTION parallel_copy_trig_func() RETURNS TRIGGER
+LANGUAGE plpgsql PARALLEL SAFE AS $$
+BEGIN
+ RETURN NEW;
+END;
+$$;
+
+-- before insert row trigger
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- after insert row trigger
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- before insert statement trigger
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- parallelism should be picked, since the trigger function is parallel safe
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- after insert statement trigger
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- transition table is involved
+CREATE TRIGGER parallel_copy_trig
+AFTER INSERT ON test_parallel_copy REFERENCING NEW TABLE AS new_table
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- make trigger function parallel unsafe
+ALTER FUNCTION parallel_copy_trig_func PARALLEL UNSAFE;
+
+-- before statement trigger has a parallel unsafe function
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy
+FOR EACH STATEMENT
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+-- no parallelism should be picked
+COPY test_parallel_copy FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+SELECT count(*) FROM test_parallel_copy;
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy;
+
+-- instead of insert trigger, no parallelism should be picked
+COPY instead_of_insert_tbl_view FROM stdin WITH(PARALLEL 1);;
+test1
+\.
+
+SELECT count(*) FROM instead_of_insert_tbl_view;
+
+-- parallel copy test for a partitioned table with a before insert trigger on
+-- one of the partition
+ALTER FUNCTION parallel_copy_trig_func PARALLEL SAFE;
+
+CREATE TABLE test_parallel_copy_part (
+ a INT,
+ b INT,
+ c TEXT default 'stuff',
+ d TEXT,
+ e TEXT
+) PARTITION BY LIST (b);
+
+CREATE TABLE test_parallel_copy_part_a1 (c TEXT, b INT, a INT, e TEXT, d TEXT);
+
+CREATE TABLE test_parallel_copy_part_a2 (a INT, c TEXT, b INT, d TEXT, e TEXT);
+
+ALTER TABLE test_parallel_copy_part ATTACH PARTITION test_parallel_copy_part_a1 FOR VALUES IN(1);
+
+ALTER TABLE test_parallel_copy_part ATTACH PARTITION test_parallel_copy_part_a2 FOR VALUES IN(2);
+
+CREATE TRIGGER parallel_copy_trig
+BEFORE INSERT ON test_parallel_copy_part_a2
+FOR EACH ROW
+EXECUTE PROCEDURE parallel_copy_trig_func();
+
+COPY test_parallel_copy_part FROM stdin WITH (PARALLEL 1);
+1 1 test_c1 test_d1 test_e1
+2 2 test_c2 test_d2 test_e2
+\.
+
+SELECT count(*) FROM test_parallel_copy_part;
+
+DROP TRIGGER parallel_copy_trig ON test_parallel_copy_part_a2;
+
-- clean up
+DROP TABLE test_copy_ri;
+DROP TABLE test_copy_pk;
+DROP TABLE test_copy_expr;
+DROP TABLE testeoc;
+DROP TABLE testnl;
DROP TABLE forcetest;
+DROP TABLE test_parallel_copy;
+DROP TABLE test_parallel_copy_unlogged;
+DROP TABLE test_parallel_copy_part;
+DROP TABLE testserial;
+DROP TABLE testnull;
DROP TABLE vistest;
DROP FUNCTION truncate_in_subxact();
+DROP FUNCTION parallel_copy_trig_func();
DROP TABLE x, y;
DROP TABLE rls_t1 CASCADE;
DROP ROLE regress_rls_copy_user;
--
1.8.3.1