agora inbox for pgsql-hackers@postgresql.orghelp / color / mirror / Atom feed
[PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing 7+ messages / 2 participants [nested] [flat]
* [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successively lower levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key of the tuple to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 30 +++++++++++++++++++++++------- src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 25 insertions(+), 11 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index 3f8a950f37..9b2a71d0d5 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1661,7 +1661,10 @@ get_partition_for_tuple(PartitionDispatch *pd, bool isnull[PARTITION_MAX_KEYS]; int cur_offset, cur_index; - int i; + int i, + result; + ExprContext *ecxt = GetPerTupleExprContext(estate); + TupleTableSlot *ecxt_scantuple_old = ecxt->ecxt_scantuple; /* start with the root partitioned table */ parent = pd[0]; @@ -1690,7 +1693,15 @@ get_partition_for_tuple(PartitionDispatch *pd, slot = myslot; } - /* Extract partition key from tuple */ + /* + * Extract partition key from tuple. Expression evaluation machinery + * that FormPartitionKeyDatum() invokes expects ecxt_scantuple to + * point to the correct tuple slot. The slot might have changed from + * what was used for the parent table if the table of the current + * partitioning level has different tuple descriptor from the parent. + * So update ecxt_scantuple accordingly. + */ + ecxt->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) @@ -1745,16 +1756,21 @@ get_partition_for_tuple(PartitionDispatch *pd, */ if (cur_index < 0) { + result = -1; *failed_at = RelationGetRelid(parent->reldesc); - return -1; + break; } - else if (parent->indexes[cur_index] < 0) - parent = pd[-parent->indexes[cur_index]]; - else + else if (parent->indexes[cur_index] >= 0) + { + result = parent->indexes[cur_index]; break; + } + else + parent = pd[-parent->indexes[cur_index]]; } - return parent->indexes[cur_index]; + ecxt->ecxt_scantuple = ecxt_scantuple_old; + return result; } /* diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index e6edcc06c2..8cb9691056 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3191,9 +3191,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index 538fe5b181..81af3ef497 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -320,7 +320,7 @@ drop table part_ee_ff, part_gg2_2, part_gg2_1, part_gg2, part_gg1, part_gg; drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 3d5138a8e0..454e1ce2e7 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -193,7 +193,7 @@ drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------94CDD3BCE9D5AAD7A77C6456 Content-Type: text/x-diff; name="0002-Fix-some-issues-with-views-and-partitioned-tables.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0002-Fix-some-issues-with-views-and-partitioned-tables.patch" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successively lower levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key of the tuple to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 29 ++++++++++++++++++++++------- src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 24 insertions(+), 11 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index f54e1bdf3f..0de1cf245a 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1643,7 +1643,10 @@ get_partition_for_tuple(PartitionDispatch *pd, bool isnull[PARTITION_MAX_KEYS]; int cur_offset, cur_index; - int i; + int i, + result; + ExprContext *ecxt = GetPerTupleExprContext(estate); + TupleTableSlot *ecxt_scantuple_old = ecxt->ecxt_scantuple; /* start with the root partitioned table */ parent = pd[0]; @@ -1672,7 +1675,14 @@ get_partition_for_tuple(PartitionDispatch *pd, slot = myslot; } - /* Extract partition key from tuple */ + /* + * Extract partition key from tuple; FormPartitionKeyDatum() expects + * ecxt_scantuple to point to the correct tuple slot (which might be + * different from the slot we received from the caller if the + * partitioned table of the current level has different tuple + * descriptor from its parent). + */ + ecxt->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) @@ -1727,16 +1737,21 @@ get_partition_for_tuple(PartitionDispatch *pd, */ if (cur_index < 0) { + result = -1; *failed_at = RelationGetRelid(parent->reldesc); - return -1; + break; } - else if (parent->indexes[cur_index] < 0) - parent = pd[-parent->indexes[cur_index]]; - else + else if (parent->indexes[cur_index] >= 0) + { + result = parent->indexes[cur_index]; break; + } + else + parent = pd[-parent->indexes[cur_index]]; } - return parent->indexes[cur_index]; + ecxt->ecxt_scantuple = ecxt_scantuple_old; + return result; } /* diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index ff277d300a..6a9bc8372f 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3167,9 +3167,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index ca3134c34c..1c7b8047ee 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -302,7 +302,7 @@ drop cascades to table part_ee_ff1 drop cascades to table part_ee_ff2 -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 09c9879da1..c25dc14575 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -173,7 +173,7 @@ drop table list_parted cascade; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------36267A5A88CA9EA4AEC9E6E5 Content-Type: text/x-diff; name="0002-No-multi-insert-and-bulk-insert-when-COPYing-into-pa.patch" Content-Transfer-Encoding: 8bit Content-Disposition: attachment; filename*0="0002-No-multi-insert-and-bulk-insert-when-COPYing-into-pa.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH 2/8] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successively lower levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key of the tuple to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 29 ++++++++++++++++++++++------- src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 24 insertions(+), 11 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index 874e69d8d6..e540fc16d0 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1642,7 +1642,10 @@ get_partition_for_tuple(PartitionDispatch *pd, bool isnull[PARTITION_MAX_KEYS]; int cur_offset, cur_index; - int i; + int i, + result; + ExprContext *ecxt = GetPerTupleExprContext(estate); + TupleTableSlot *ecxt_scantuple_old = ecxt->ecxt_scantuple; /* start with the root partitioned table */ parent = pd[0]; @@ -1671,7 +1674,14 @@ get_partition_for_tuple(PartitionDispatch *pd, slot = myslot; } - /* Extract partition key from tuple */ + /* + * Extract partition key from tuple; FormPartitionKeyDatum() expects + * ecxt_scantuple to point to the correct tuple slot (which might be + * different from the slot we received from the caller if the + * partitioned table of the current level has different tuple + * descriptor from its parent). + */ + ecxt->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) @@ -1726,16 +1736,21 @@ get_partition_for_tuple(PartitionDispatch *pd, */ if (cur_index < 0) { + result = -1; *failed_at = RelationGetRelid(parent->reldesc); - return -1; + break; } - else if (parent->indexes[cur_index] < 0) - parent = pd[-parent->indexes[cur_index]]; - else + else if (parent->indexes[cur_index] >= 0) + { + result = parent->indexes[cur_index]; break; + } + else + parent = pd[-parent->indexes[cur_index]]; } - return parent->indexes[cur_index]; + ecxt->ecxt_scantuple = ecxt_scantuple_old; + return result; } /* diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index 5457f8fbde..67e46729f3 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3191,9 +3191,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index 729d9ebbbc..b8e74caee8 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -320,7 +320,7 @@ drop table part_ee_ff, part_gg2_2, part_gg2_1, part_gg2, part_gg1, part_gg; drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 5509555fc5..2154d01c56 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -193,7 +193,7 @@ drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------49BF125E4F135FB3D50EF5A9 Content-Type: text/x-diff; name="0003-Fix-RETURNING-to-work-correctly-after-tuple-routing.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Fix-RETURNING-to-work-correctly-after-tuple-routing.pat"; filename*1="ch" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successively lower levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key of the tuple to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 29 ++++++++++++++++++++++------- src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 24 insertions(+), 11 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index f54e1bdf3f..0de1cf245a 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1643,7 +1643,10 @@ get_partition_for_tuple(PartitionDispatch *pd, bool isnull[PARTITION_MAX_KEYS]; int cur_offset, cur_index; - int i; + int i, + result; + ExprContext *ecxt = GetPerTupleExprContext(estate); + TupleTableSlot *ecxt_scantuple_old = ecxt->ecxt_scantuple; /* start with the root partitioned table */ parent = pd[0]; @@ -1672,7 +1675,14 @@ get_partition_for_tuple(PartitionDispatch *pd, slot = myslot; } - /* Extract partition key from tuple */ + /* + * Extract partition key from tuple; FormPartitionKeyDatum() expects + * ecxt_scantuple to point to the correct tuple slot (which might be + * different from the slot we received from the caller if the + * partitioned table of the current level has different tuple + * descriptor from its parent). + */ + ecxt->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) @@ -1727,16 +1737,21 @@ get_partition_for_tuple(PartitionDispatch *pd, */ if (cur_index < 0) { + result = -1; *failed_at = RelationGetRelid(parent->reldesc); - return -1; + break; } - else if (parent->indexes[cur_index] < 0) - parent = pd[-parent->indexes[cur_index]]; - else + else if (parent->indexes[cur_index] >= 0) + { + result = parent->indexes[cur_index]; break; + } + else + parent = pd[-parent->indexes[cur_index]]; } - return parent->indexes[cur_index]; + ecxt->ecxt_scantuple = ecxt_scantuple_old; + return result; } /* diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index ff277d300a..6a9bc8372f 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3167,9 +3167,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index ca3134c34c..1c7b8047ee 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -302,7 +302,7 @@ drop cascades to table part_ee_ff1 drop cascades to table part_ee_ff2 -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 09c9879da1..c25dc14575 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -173,7 +173,7 @@ drop table list_parted cascade; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------35DA5B82994CF4AD40E20FE2 Content-Type: text/x-diff; name="0002-No-multi-insert-and-bulk-insert-when-COPYing-into-pa.patch" Content-Transfer-Encoding: 8bit Content-Disposition: attachment; filename*0="0002-No-multi-insert-and-bulk-insert-when-COPYing-into-pa.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH 1/2] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successive levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key expressions to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 2 ++ src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index fca874752f..f9daf8052d 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1647,6 +1647,7 @@ get_partition_for_tuple(PartitionDispatch *pd, PartitionDesc partdesc = parent->partdesc; TupleTableSlot *myslot = parent->tupslot; TupleConversionMap *map = parent->tupmap; + ExprContext *econtext = GetPerTupleExprContext(estate); /* Quick exit */ if (partdesc->nparts == 0) @@ -1667,6 +1668,7 @@ get_partition_for_tuple(PartitionDispatch *pd, } /* Extract partition key from tuple */ + econtext->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index bca34a509c..1d699c1dab 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3107,9 +3107,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index 49f667b119..ae54625034 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -302,7 +302,7 @@ drop cascades to table part_ee_ff1 drop cascades to table part_ee_ff2 -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 08dc068de8..9d3a34073c 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -173,7 +173,7 @@ drop table list_parted cascade; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------E7074D3175BCE043220A92BA Content-Type: text/x-diff; name="0002-No-BulkInsertState-when-tuple-routing-is-in-action.patch" Content-Transfer-Encoding: 8bit Content-Disposition: attachment; filename*0="0002-No-BulkInsertState-when-tuple-routing-is-in-action.patc"; filename*1="h" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH 2/8] Set ecxt_scantuple correctly for tuple-routing @ 2016-12-28 01:10 amit <amitlangote09@gmail.com> 0 siblings, 0 replies; 7+ messages in thread From: amit @ 2016-12-28 01:10 UTC (permalink / raw) In 2ac3ef7a01df859c62d0a02333b646d65eaec5ff, we changed things so that it's possible for a different TupleTableSlot to be used for partitioned tables at successively lower levels. If we do end up changing the slot from the original, we must update ecxt_scantuple to point to the new one for partition key of the tuple to be computed correctly. Also update the regression tests so that the code manipulating ecxt_scantuple is covered. Reported by: Rajkumar Raghuwanshi Patch by: Amit Langote Reports: https://www.postgresql.org/message-id/CAKcux6%3Dm1qyqB2k6cjniuMMrYXb75O-MB4qGQMu8zg-iGGLjDw%40mail.g... --- src/backend/catalog/partition.c | 29 ++++++++++++++++++++++------- src/backend/executor/execMain.c | 2 -- src/test/regress/expected/insert.out | 2 +- src/test/regress/sql/insert.sql | 2 +- 4 files changed, 24 insertions(+), 11 deletions(-) diff --git a/src/backend/catalog/partition.c b/src/backend/catalog/partition.c index 874e69d8d6..e540fc16d0 100644 --- a/src/backend/catalog/partition.c +++ b/src/backend/catalog/partition.c @@ -1642,7 +1642,10 @@ get_partition_for_tuple(PartitionDispatch *pd, bool isnull[PARTITION_MAX_KEYS]; int cur_offset, cur_index; - int i; + int i, + result; + ExprContext *ecxt = GetPerTupleExprContext(estate); + TupleTableSlot *ecxt_scantuple_old = ecxt->ecxt_scantuple; /* start with the root partitioned table */ parent = pd[0]; @@ -1671,7 +1674,14 @@ get_partition_for_tuple(PartitionDispatch *pd, slot = myslot; } - /* Extract partition key from tuple */ + /* + * Extract partition key from tuple; FormPartitionKeyDatum() expects + * ecxt_scantuple to point to the correct tuple slot (which might be + * different from the slot we received from the caller if the + * partitioned table of the current level has different tuple + * descriptor from its parent). + */ + ecxt->ecxt_scantuple = slot; FormPartitionKeyDatum(parent, slot, estate, values, isnull); if (key->strategy == PARTITION_STRATEGY_RANGE) @@ -1726,16 +1736,21 @@ get_partition_for_tuple(PartitionDispatch *pd, */ if (cur_index < 0) { + result = -1; *failed_at = RelationGetRelid(parent->reldesc); - return -1; + break; } - else if (parent->indexes[cur_index] < 0) - parent = pd[-parent->indexes[cur_index]]; - else + else if (parent->indexes[cur_index] >= 0) + { + result = parent->indexes[cur_index]; break; + } + else + parent = pd[-parent->indexes[cur_index]]; } - return parent->indexes[cur_index]; + ecxt->ecxt_scantuple = ecxt_scantuple_old; + return result; } /* diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index 5457f8fbde..67e46729f3 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -3191,9 +3191,7 @@ ExecFindPartition(ResultRelInfo *resultRelInfo, PartitionDispatch *pd, { int result; Oid failed_at; - ExprContext *econtext = GetPerTupleExprContext(estate); - econtext->ecxt_scantuple = slot; result = get_partition_for_tuple(pd, slot, estate, &failed_at); if (result < 0) { diff --git a/src/test/regress/expected/insert.out b/src/test/regress/expected/insert.out index 729d9ebbbc..b8e74caee8 100644 --- a/src/test/regress/expected/insert.out +++ b/src/test/regress/expected/insert.out @@ -320,7 +320,7 @@ drop table part_ee_ff, part_gg2_2, part_gg2_1, part_gg2, part_gg1, part_gg; drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; diff --git a/src/test/regress/sql/insert.sql b/src/test/regress/sql/insert.sql index 5509555fc5..2154d01c56 100644 --- a/src/test/regress/sql/insert.sql +++ b/src/test/regress/sql/insert.sql @@ -193,7 +193,7 @@ drop table part_aa_bb, part_cc_dd, part_null, list_parted; -- more tests for certain multi-level partitioning scenarios create table p (a int, b int) partition by range (a, b); -create table p1 (b int, a int not null) partition by range (b); +create table p1 (b int not null, a int not null) partition by range ((b+0)); create table p11 (like p1); alter table p11 drop a; alter table p11 add a int; -- 2.11.0 --------------CF13DAB8ACCD266FF78EDA60 Content-Type: text/x-diff; name="0003-Fix-RETURNING-to-work-correctly-after-tuple-routing.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Fix-RETURNING-to-work-correctly-after-tuple-routing.pat"; filename*1="ch" ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v51 06/10] Error out any process that would block at REPACK @ 2026-04-01 15:35 Antonin Houska <ah@cybertec.at> 0 siblings, 0 replies; 7+ messages in thread From: Antonin Houska @ 2026-04-01 15:35 UTC (permalink / raw) Any process waiting on REPACK to release its lock would actually cause it to deadlock when it tries to upgrade its lock to AEL, losing all work done to that point. We avoid this by teaching the deadlock detector to raise an error when this condition is detected. --- src/backend/commands/repack.c | 60 ++++++++++---- src/backend/storage/lmgr/deadlock.c | 15 ++++ src/include/storage/proc.h | 6 +- src/test/modules/injection_points/Makefile | 1 + .../expected/repack_deadlock.out | 63 ++++++++++++++ src/test/modules/injection_points/meson.build | 1 + .../specs/repack_deadlock.spec | 83 +++++++++++++++++++ 7 files changed, 210 insertions(+), 19 deletions(-) create mode 100644 src/test/modules/injection_points/expected/repack_deadlock.out create mode 100644 src/test/modules/injection_points/specs/repack_deadlock.spec diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 03829892d57..d6e446d582d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -279,6 +279,21 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) /* Determine the lock mode to use. */ lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); + /* + * If in concurrent mode, set the PROC_IN_CONCURRENT_REPACK flag. This + * makes the deadlock checker cause anyone that would conflict with us to + * error out. It's important to set this flag ahead of actually locking + * the relation; it won't of course affect anyone until we do have a lock + * that others can conflict with. + */ + if ((params.options & CLUOPT_CONCURRENT) != 0) + { + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + } + /* * If a single relation is specified, process it and we're done ... unless * the relation is a partitioned table, in which case we fall through. @@ -479,11 +494,8 @@ RepackLockLevel(bool concurrent) * If indexOid is InvalidOid, the table will be rewritten in physical order * instead of index order. * - * Note that, in the concurrent case, the function releases the lock at some - * point, in order to get AccessExclusiveLock for the final steps (i.e. to - * swap the relation files). To make things simpler, the caller should expect - * OldHeap to be closed on return, regardless CLUOPT_CONCURRENT. (The - * AccessExclusiveLock is kept till the end of the transaction.) + * On return, OldHeap is closed but locked with AccessExclusiveLock - the lock + * will be released at end of the transaction. * * 'cmd' indicates which command is being executed, to be used for error * messages. @@ -515,10 +527,12 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, /* * Make sure we're not in a transaction block. * - * The reason is that repack_setup_logical_decoding() could deadlock - * if there's an XID already assigned. It would be possible to run in - * a transaction block if we had no XID, but this restriction is - * simpler for users to understand and we don't lose anything. + * The reason is that repack_setup_logical_decoding() could wait + * indefinitely for our XID to complete. (The deadlock detector would + * not recognize it because we'd be waiting for ourselves, i.e. no + * real lock conflict.) It would be possible to run in a transaction + * block if we had no XID, but this restriction is simpler for users + * to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -1001,10 +1015,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * Note that the worker has to wait for all transactions with XID * already assigned to finish. If some of those transactions is * waiting for a lock conflicting with ShareUpdateExclusiveLock on our - * table (e.g. it runs CREATE INDEX), we can end up in a deadlock. - * Not sure this risk is worth unlocking/locking the table (and its - * clustering index) and checking again if it's still eligible for - * REPACK CONCURRENTLY. + * table (e.g. it runs CREATE INDEX), it should encounter ERROR in the + * deadlock checking code. */ start_repack_decoding_worker(tableOid); @@ -3093,7 +3105,19 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock); /* - * Tuples and pages of the old heap will be gone, but the heap will stay. + * Now that we have all access-exclusive locks on all relations, we no + * longer want other processes to error out when trying to acquire a + * conflicting lock. Therefore, unset our flag. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags &= ~PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + + /* + * Tuples and pages of the old heap will be gone, but the heap itself will + * stay. In order for predicate locks to continue to work, convert them + * to relation-level locks. We do this both for table and indexes. */ TransferPredicateLocksToHeapRelation(OldHeap); foreach_ptr(RelationData, index, indexrels) @@ -3366,9 +3390,11 @@ start_repack_decoding_worker(Oid relid) /* * The decoding setup must be done before the caller can have XID assigned - * for any reason, otherwise the worker might end up in a deadlock, - * waiting for the caller's transaction to end. Therefore wait here until - * the worker indicates that it has the logical decoding initialized. + * for any reason, otherwise the worker might end up waiting for the + * caller's transaction to end. (Deadlock detector does not consider this + * a conflict because the worker is in the same locking group as the + * backend that launched it.) Therefore wait here until the worker + * indicates that it has the logical decoding initialized. */ ConditionVariablePrepareToSleep(&shared->cv); for (;;) diff --git a/src/backend/storage/lmgr/deadlock.c b/src/backend/storage/lmgr/deadlock.c index b8962d875b6..c20ac682b0d 100644 --- a/src/backend/storage/lmgr/deadlock.c +++ b/src/backend/storage/lmgr/deadlock.c @@ -620,6 +620,21 @@ FindLockCycleRecurseMember(PGPROC *checkProc, proc->statusFlags & PROC_IS_AUTOVACUUM) blocking_autovacuum_proc = proc; + /* + * Similarly, if we note that we're blocked by some + * process running REPACK (CONCURRENTLY), just fail. That + * process is going to upgrade its lock at some point, and + * it would be inappropriate for any other process to + * cause that to fail. + */ + if (checkProc == MyProc && + proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + ereport(ERROR, + errcode(ERRCODE_OBJECT_IN_USE), + errmsg("could not wait for concurrent REPACK"), + errdetail("Process %d waits for REPACK running on process %d", + MyProc->pid, proc->pid)); + /* We're done looking at this proclock */ break; } diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..8ad9718f3d6 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,12 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_CONCURRENT_REPACK 0x40 /* REPACK (CONCURRENTLY) */ -/* flags reset at EOXact */ +/* flags reset at EOXact. A bit of a misnomer ... */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | \ + PROC_IN_CONCURRENT_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile index 2cd7d87c533..f7663859fe2 100644 --- a/src/test/modules/injection_points/Makefile +++ b/src/test/modules/injection_points/Makefile @@ -15,6 +15,7 @@ REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress ISOLATION = basic \ inplace \ repack \ + repack_deadlock \ repack_toast \ syscache-update-pruned \ heap_lock_update diff --git a/src/test/modules/injection_points/expected/repack_deadlock.out b/src/test/modules/injection_points/expected/repack_deadlock.out new file mode 100644 index 00000000000..a86e4767536 --- /dev/null +++ b/src/test/modules/injection_points/expected/repack_deadlock.out @@ -0,0 +1,63 @@ +Parsed test spec with 2 sessions + +starting permutation: wait_before_lock add_column wakeup_before_lock check1 +injection_points_attach +----------------------- + +(1 row) + +step wait_before_lock: + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; + <waiting ...> +step add_column: + alter table repack_deadlock add column noise text; + <waiting ...> +step add_column: <... completed> +ERROR: could not wait for concurrent REPACK +step wakeup_before_lock: + SELECT injection_points_wakeup('repack-concurrently-before-lock'); + +injection_points_wakeup +----------------------- + +(1 row) + +step wait_before_lock: <... completed> +step check1: + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; + +count +----- + 1 +(1 row) + +i|j +-+- +1|1 +2|2 +3|3 +4|4 +(4 rows) + +count +----- + 4 +(1 row) + +injection_points_detach +----------------------- + +(1 row) + diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build index a414abb924b..1cd88d6db65 100644 --- a/src/test/modules/injection_points/meson.build +++ b/src/test/modules/injection_points/meson.build @@ -46,6 +46,7 @@ tests += { 'basic', 'inplace', 'repack', + 'repack_deadlock', 'repack_toast', 'syscache-update-pruned', 'heap_lock_update', diff --git a/src/test/modules/injection_points/specs/repack_deadlock.spec b/src/test/modules/injection_points/specs/repack_deadlock.spec new file mode 100644 index 00000000000..9d23a6588c2 --- /dev/null +++ b/src/test/modules/injection_points/specs/repack_deadlock.spec @@ -0,0 +1,83 @@ +# Test REPACK with a concurrent transaction that would cause a deadlock +setup +{ + CREATE EXTENSION injection_points; + + CREATE TABLE repack_deadlock(i int PRIMARY KEY, j int); + INSERT INTO repack_deadlock(i, j) VALUES (1, 1), (2, 2), (3, 3), (4, 4); + + CREATE TABLE relfilenodes(node oid); + + CREATE TABLE data_s1(i int, j int); + CREATE TABLE data_s2(i int, j int); +} + +teardown +{ + DROP TABLE repack_deadlock; + DROP EXTENSION injection_points; + + DROP TABLE relfilenodes; + DROP TABLE data_s1; + DROP TABLE data_s2; +} + +session s1 +setup +{ + SELECT injection_points_set_local(); + SELECT injection_points_attach('repack-concurrently-before-lock', 'wait'); +} +# Perform the initial load and wait for s2 to do some data changes. +step wait_before_lock +{ + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; +} +# Check the table from the perspective of s1. +# +# Besides the contents, we also check that relfilenode has changed. + +# Have each session write the contents into a table and use FULL JOIN to check +# if the outputs are identical. +step check1 +{ + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; +} +teardown +{ + SELECT injection_points_detach('repack-concurrently-before-lock'); +} + +session s2 +# Change the existing data. UPDATE changes both key and non-key columns. Also +# update one row twice to test whether tuple version generated by this session +# can be found. +step add_column +{ + alter table repack_deadlock add column noise text; +} + +step wakeup_before_lock +{ + SELECT injection_points_wakeup('repack-concurrently-before-lock'); +} + +# Test if data changes introduced while one session is performing REPACK +# CONCURRENTLY find their way into the table. +permutation + wait_before_lock + add_column + wakeup_before_lock + check1 -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0007-Check-for-transaction-block-early-in-ExecRepack.patch" ^ permalink raw reply [nested|flat] 7+ messages in thread
end of thread, other threads:[~2026-04-01 15:35 UTC | newest] Thread overview: 7+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2016-12-28 01:10 [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2016-12-28 01:10 [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2016-12-28 01:10 [PATCH 2/8] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2016-12-28 01:10 [PATCH 1/3] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2016-12-28 01:10 [PATCH 1/2] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2016-12-28 01:10 [PATCH 2/8] Set ecxt_scantuple correctly for tuple-routing amit <amitlangote09@gmail.com> 2026-04-01 15:35 [PATCH v51 06/10] Error out any process that would block at REPACK Antonin Houska <ah@cybertec.at>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox