agora inbox for pgsql-hackers@postgresql.org
help / color / mirror / Atom feedFrom: Antonin Houska <ah@cybertec.at>
To: Alvaro Herrera <alvherre@alvh.no-ip.org>
Cc: Mihail Nikalayeu <mihailnikalayeu@gmail.com>
Cc: Pg Hackers <pgsql-hackers@lists.postgresql.org>
Cc: Robert Treat <rob@xzilla.net>
Subject: Re: Adding REPACK [concurrently]
Date: Sat, 13 Dec 2025 19:48:39 +0100
Message-ID: <210036.1765651719@localhost> (raw)
In-Reply-To: <202512091915.ws6fk7csn76r@alvherre.pgsql>
References: <202512091915.ws6fk7csn76r@alvherre.pgsql>
Alvaro Herrera <alvherre@alvh.no-ip.org> wrote:
> Hello, many thanks for the new version. Here's a very quick proposal
> for a new top-of-file comment on cluster.c,
The comment matches 0005, but I had to adjust it for 0004 (no background
worker there). Also, the worker writes the changes to a file rather than
tuplestore (storage/sharedfileset.h seems to me an easier way to pass the data
from one process to another) Besides that I made the following changes:
"bloat is greatly reduced" -> "bloat is eliminated"
and
"table, and to cope with" -> "table. To cope with"
> I haven't read build_relation_finish_concurrent() yet to understand how
> exactly do we do the lock upgrade, which I think is an important point
> we should address in this comment. Also not addressed is how exactly we
> handle indexes. Feel free to correct this, reword it or include any
> additional details that you think are important.
ok, I'll get back to the earlier parts of the set, including this, in the
beginning of January. Regarding indexes, one thing I've noticed recently that
they get locked in build_new_indexes(), but maybe it should happen earlier.
> (At this point we could just as well rename the file to repack.c, since
> very little of the original remains. But let's discuss that later.)
ok. Do you mean only the file or the functions as well? (I'm not going to do
that now, w/o that discussion.)
Attached here is a new version of the patch set. Its rebased and extended one
more time: 0006 is a PoC of the "snapshot resetting" technique, as discussed
elsewhere with Mihail Nikalayeu and Matthias van de Meent. The way snapshot
are generated here is different though: we need the snapshots from logical
replication's snapbuild.c, not those from procarray.c. More information is in
the commit message.
I do not insist that this should go to PG 19, just needed some confidence that
it's doable, as well as some feedback. There are no tests for this yet, but
I've played with it for a while and checked the behavior using debugger. I'm
curious to hear if the design is sound.
While working on that, I fixed some problems in 0004 and 0005 too. It
shouldn't be difficult to identify them using git, if needed.
Even if 0005 and 0006 won't land in PG19, these parts show that some
refactoring may be needed regarding the AM callback
table_relation_copy_for_cluster(). The parts 0004, 0005 and 0006 each change
the argument list. It wouldn't be perfect if both PG 19 and 20 changed the
API. I think we should reconsider which arguments are generic and which are
rather AM-specific. Maybe we should then add an opaque pointer (void *) for
the AM-specific information. REPACK could then use it to pass the
CONCURRENTLY-specific information.
I'm now going to prioritize the parts <= 0004.
--
Antonin Houska
Web: https://www.cybertec-postgresql.com
From 6279394135f2b693b6fffd174822509e0a067cbf Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 4/6] Add CONCURRENTLY option to REPACK command.
The REPACK command copies the relation data into a new file, creates new
indexes and eventually swaps the files. To make sure that the old file does
not change during the copying, the relation is locked in an exclusive mode,
which prevents applications from both reading and writing. (To keep the data
consistent, we'd only need to prevent the applications from writing, but even
reading needs to be blocked before we can swap the files - otherwise some
applications could continue using the old file. Since we should not request a
stronger lock without releasing the weaker one first, we acquire the exclusive
lock in the beginning and keep it till the end of the processing.)
This patch introduces an alternative workflow, which only requires the
exclusive lock when the relation (and index) files are being swapped.
(Supposedly, the swapping should be pretty fast.) On the other hand, when we
copy the data to the new file, we allow applications to read from the relation
and even to write to it.
First, we scan the relation using a "historic snapshot", and insert all the
tuples satisfying this snapshot into the new file.
Second, logical decoding is used to capture the data changes done by
applications during the copying (i.e. changes that do not satisfy the historic
snapshot mentioned above), and those are applied to the new file before we
acquire the exclusive lock that we need to swap the files. (Of course, more
data changes can take place while we are waiting for the lock - these will be
applied to the new file after we have acquired the lock, before we swap the
files.)
Since the logical decoding system, during its startup, waits until all the
transactions which already have XID assigned have finished, there is a risk of
deadlock if a transaction that already changed anything in the database tries
to acquire a conflicting lock on the table REPACK CONCURRENTLY is working
on. As an example, consider transaction running CREATE INDEX command on the
table that is being REPACKed CONCURRENTLY. On the other hand, DML commands
(INSERT, UPDATE, DELETE) are not a problem as their lock does not conflict
with REPACK CONCURRENTLY.
The current approach is that we accept the risk. If we tried to avoid it, it'd
be necessary to unlock the table before the logical decoding is setup and lock
it again afterwards. Such temporary unlocking would imply re-checking if the
table still meets all the requirements for REPACK CONCURRENTLY.
Like the existing implementation of REPACK, the variant with the CONCURRENTLY
option also requires an extra space for the new relation and index files
(which coexist with the old files for some time). In addition, the
CONCURRENTLY option might introduce a lag in releasing WAL segments for
archiving / recycling. This is due to the decoding of the data changes done by
applications concurrently. When copying the table contents into the new file,
we check the lag periodically. If it exceeds the size of a WAL segment, we
decode all the available WAL before resuming the copying. (Of course, the
changes are not applied until the whole table contents is copied.) A
background worker might be a better approach for the decoding - let's consider
implementing it in the future.
The WAL records produced by running DML commands on the new relation do not
contain enough information to be processed by the logical decoding system. All
we need from the new relation is the file (relfilenode), while the actual
relation is eventually dropped. Thus there is no point in replaying the DMLs
anywhere.
---
doc/src/sgml/monitoring.sgml | 37 +-
doc/src/sgml/mvcc.sgml | 12 +-
doc/src/sgml/ref/repack.sgml | 129 +-
src/Makefile | 1 +
src/backend/access/heap/heapam.c | 34 +-
src/backend/access/heap/heapam_handler.c | 227 ++-
src/backend/access/heap/rewriteheap.c | 6 +-
src/backend/catalog/system_views.sql | 19 +-
src/backend/commands/cluster.c | 1599 +++++++++++++++--
src/backend/commands/matview.c | 2 +-
src/backend/commands/tablecmds.c | 1 +
src/backend/commands/vacuum.c | 12 +-
src/backend/meson.build | 1 +
src/backend/replication/logical/decode.c | 94 +
src/backend/replication/logical/snapbuild.c | 21 +
.../replication/pgoutput_repack/Makefile | 32 +
.../replication/pgoutput_repack/meson.build | 18 +
.../pgoutput_repack/pgoutput_repack.c | 240 +++
.../storage/lmgr/generate-lwlocknames.pl | 2 +-
src/backend/utils/time/snapmgr.c | 3 +-
src/bin/psql/tab-complete.in.c | 4 +-
src/include/access/heapam.h | 5 +-
src/include/access/heapam_xlog.h | 2 +
src/include/access/tableam.h | 10 +
src/include/commands/cluster.h | 90 +-
src/include/commands/progress.h | 17 +-
src/include/replication/snapbuild.h | 1 +
src/include/storage/lockdefs.h | 4 +-
src/include/utils/snapmgr.h | 2 +
src/test/modules/injection_points/Makefile | 3 +
.../injection_points/expected/repack.out | 113 ++
.../expected/repack_toast.out | 64 +
.../modules/injection_points/logical.conf | 1 +
src/test/modules/injection_points/meson.build | 4 +
.../injection_points/specs/repack.spec | 142 ++
.../injection_points/specs/repack_toast.spec | 105 ++
src/test/regress/expected/rules.out | 19 +-
src/tools/pgindent/typedefs.list | 5 +
38 files changed, 2845 insertions(+), 236 deletions(-)
create mode 100644 src/backend/replication/pgoutput_repack/Makefile
create mode 100644 src/backend/replication/pgoutput_repack/meson.build
create mode 100644 src/backend/replication/pgoutput_repack/pgoutput_repack.c
create mode 100644 src/test/modules/injection_points/expected/repack.out
create mode 100644 src/test/modules/injection_points/expected/repack_toast.out
create mode 100644 src/test/modules/injection_points/logical.conf
create mode 100644 src/test/modules/injection_points/specs/repack.spec
create mode 100644 src/test/modules/injection_points/specs/repack_toast.spec
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index b07fe3294cd..ae56b09aeba 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -6202,14 +6202,35 @@ FROM pg_stat_get_backend_idset() AS backendid;
<row>
<entry role="catalog_table_entry"><para role="column_definition">
- <structfield>heap_tuples_written</structfield> <type>bigint</type>
+ <structfield>heap_tuples_inserted</structfield> <type>bigint</type>
</para>
<para>
- Number of heap tuples written.
+ Number of heap tuples inserted.
This counter only advances when the phase is
<literal>seq scanning heap</literal>,
- <literal>index scanning heap</literal>
- or <literal>writing new heap</literal>.
+ <literal>index scanning heap</literal>,
+ <literal>writing new heap</literal>
+ or <literal>catch-up</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_updated</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples updated.
+ This counter only advances when the phase is <literal>catch-up</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_deleted</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples deleted.
+ This counter only advances when the phase is <literal>catch-up</literal>.
</para></entry>
</row>
@@ -6290,6 +6311,14 @@ FROM pg_stat_get_backend_idset() AS backendid;
<command>REPACK</command> is currently writing the new heap.
</entry>
</row>
+ <row>
+ <entry><literal>catch-up</literal></entry>
+ <entry>
+ <command>REPACK CONCURRENTLY</command> is currently processing the DML
+ commands that other transactions executed during any of the preceding
+ phases.
+ </entry>
+ </row>
<row>
<entry><literal>swapping relation files</literal></entry>
<entry>
diff --git a/doc/src/sgml/mvcc.sgml b/doc/src/sgml/mvcc.sgml
index 049ee75a4ba..0f5c34af542 100644
--- a/doc/src/sgml/mvcc.sgml
+++ b/doc/src/sgml/mvcc.sgml
@@ -1833,15 +1833,17 @@ SELECT pg_advisory_lock(q.id) FROM
<title>Caveats</title>
<para>
- Some DDL commands, currently only <link linkend="sql-truncate"><command>TRUNCATE</command></link> and the
- table-rewriting forms of <link linkend="sql-altertable"><command>ALTER TABLE</command></link>, are not
+ Some commands, currently only <link linkend="sql-truncate"><command>TRUNCATE</command></link>, the
+ table-rewriting forms of <link linkend="sql-altertable"><command>ALTER
+ TABLE</command></link> and <command>REPACK</command> with
+ the <literal>CONCURRENTLY</literal> option, are not
MVCC-safe. This means that after the truncation or rewrite commits, the
table will appear empty to concurrent transactions, if they are using a
- snapshot taken before the DDL command committed. This will only be an
+ snapshot taken before the command committed. This will only be an
issue for a transaction that did not access the table in question
- before the DDL command started — any transaction that has done so
+ before the command started — any transaction that has done so
would hold at least an <literal>ACCESS SHARE</literal> table lock,
- which would block the DDL command until that transaction completes.
+ which would block the truncating or rewriting command until that transaction completes.
So these commands will not cause any apparent inconsistency in the
table contents for successive queries on the target table, but they
could cause visible inconsistency between the contents of the target
diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml
index 61d5c2cdef1..30c43c49069 100644
--- a/doc/src/sgml/ref/repack.sgml
+++ b/doc/src/sgml/ref/repack.sgml
@@ -28,6 +28,7 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
VERBOSE [ <replaceable class="parameter">boolean</replaceable> ]
ANALYZE [ <replaceable class="parameter">boolean</replaceable> ]
+ CONCURRENTLY [ <replaceable class="parameter">boolean</replaceable> ]
<phrase>and <replaceable class="parameter">table_and_columns</replaceable> is:</phrase>
@@ -54,7 +55,8 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
processes every table and materialized view in the current database that
the current user has the <literal>MAINTAIN</literal> privilege on. This
form of <command>REPACK</command> cannot be executed inside a transaction
- block.
+ block. Also, this form is not allowed if
+ the <literal>CONCURRENTLY</literal> option is used.
</para>
<para>
@@ -67,7 +69,8 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
When a table is being repacked, an <literal>ACCESS EXCLUSIVE</literal> lock
is acquired on it. This prevents any other database operations (both reads
and writes) from operating on the table until the <command>REPACK</command>
- is finished.
+ is finished. If you want to keep the table accessible during the repacking,
+ consider using the <literal>CONCURRENTLY</literal> option.
</para>
<refsect2 id="sql-repack-notes-on-clustering" xreflabel="Notes on Clustering">
@@ -195,6 +198,128 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
</listitem>
</varlistentry>
+ <varlistentry>
+ <term><literal>CONCURRENTLY</literal></term>
+ <listitem>
+ <para>
+ Allow other transactions to use the table while it is being repacked.
+ </para>
+
+ <para>
+ Internally, <command>REPACK</command> copies the contents of the table
+ (ignoring dead tuples) into a new file, sorted by the specified index,
+ and also creates a new file for each index. Then it swaps the old and
+ new files for the table and all the indexes, and deletes the old
+ files. The <literal>ACCESS EXCLUSIVE</literal> lock is needed to make
+ sure that the old files do not change during the processing because the
+ changes would get lost due to the swap.
+ </para>
+
+ <para>
+ With the <literal>CONCURRENTLY</literal> option, the <literal>ACCESS
+ EXCLUSIVE</literal> lock is only acquired to swap the table and index
+ files. The data changes that took place during the creation of the new
+ table and index files are captured using logical decoding
+ (<xref linkend="logicaldecoding"/>) and applied before
+ the <literal>ACCESS EXCLUSIVE</literal> lock is requested. Thus the lock
+ is typically held only for the time needed to swap the files, which
+ should be pretty short. However, the time might still be noticeable if
+ too many data changes have been done to the table while
+ <command>REPACK</command> was waiting for the lock: those changes must
+ be processed just before the files are swapped, while the
+ <literal>ACCESS EXCLUSIVE</literal> lock is being held.
+ </para>
+
+ <para>
+ Note that <command>REPACK</command> with the
+ <literal>CONCURRENTLY</literal> option does not try to order the rows
+ inserted into the table after the repacking started. Also
+ note <command>REPACK</command> might fail to complete due to DDL
+ commands executed on the table by other transactions during the
+ repacking.
+ </para>
+
+ <note>
+ <para>
+ In addition to the temporary space requirements explained in
+ <xref linkend="sql-repack-notes-on-resources"/>,
+ the <literal>CONCURRENTLY</literal> option can add to the usage of
+ temporary space a bit more. The reason is that other transactions can
+ perform DML operations which cannot be applied to the new file until
+ <command>REPACK</command> has copied all the tuples from the old
+ file. Thus the tuples inserted into the old file during the copying are
+ also stored separately in a temporary file, so they can eventually be
+ applied to the new file.
+ </para>
+
+ <para>
+ Furthermore, the data changes performed during the copying are
+ extracted from <link linkend="wal">write-ahead log</link> (WAL), and
+ this extraction (decoding) only takes place when certain amount of WAL
+ has been written. Therefore, WAL removal can be delayed by this
+ threshold. Currently the threshold is equal to the value of
+ the <link linkend="guc-wal-segment-size"><varname>wal_segment_size</varname></link>
+ configuration parameter.
+ </para>
+ </note>
+
+ <para>
+ The <literal>CONCURRENTLY</literal> option cannot be used in the
+ following cases:
+
+ <itemizedlist>
+ <listitem>
+ <para>
+ The table is <literal>UNLOGGED</literal>.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The table is partitioned.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The table is a system catalog or a <acronym>TOAST</acronym> table.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ <command>REPACK</command> is executed inside a transaction block.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The <link linkend="guc-wal-level"><varname>wal_level</varname></link>
+ configuration parameter is less than <literal>logical</literal>.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link>
+ configuration parameter does not allow for creation of an additional
+ replication slot.
+ </para>
+ </listitem>
+ </itemizedlist>
+ </para>
+
+ <warning>
+ <para>
+ <command>REPACK</command> with the <literal>CONCURRENTLY</literal>
+ option is not MVCC-safe, see <xref linkend="mvcc-caveats"/> for
+ details.
+ </para>
+ </warning>
+
+ </listitem>
+ </varlistentry>
+
<varlistentry>
<term><literal>VERBOSE</literal></term>
<listitem>
diff --git a/src/Makefile b/src/Makefile
index 2f31a2f20a7..b18c9a14ffa 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -23,6 +23,7 @@ SUBDIRS = \
interfaces \
backend/replication/libpqwalreceiver \
backend/replication/pgoutput \
+ backend/replication/pgoutput_repack \
fe_utils \
bin \
pl \
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 225f9829f22..aa2b4ca3f0a 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -60,7 +60,8 @@ static HeapTuple heap_prepare_insert(Relation relation, HeapTuple tup,
static XLogRecPtr log_heap_update(Relation reln, Buffer oldbuf,
Buffer newbuf, HeapTuple oldtup,
HeapTuple newtup, HeapTuple old_key_tuple,
- bool all_visible_cleared, bool new_all_visible_cleared);
+ bool all_visible_cleared, bool new_all_visible_cleared,
+ bool walLogical);
#ifdef USE_ASSERT_CHECKING
static void check_lock_if_inplace_updateable_rel(Relation relation,
const ItemPointerData *otid,
@@ -2803,7 +2804,7 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask)
TM_Result
heap_delete(Relation relation, const ItemPointerData *tid,
CommandId cid, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart)
+ TM_FailureData *tmfd, bool changingPart, bool walLogical)
{
TM_Result result;
TransactionId xid = GetCurrentTransactionId();
@@ -3050,7 +3051,8 @@ l1:
* Compute replica identity tuple before entering the critical section so
* we don't PANIC upon a memory allocation failure.
*/
- old_key_tuple = ExtractReplicaIdentity(relation, &tp, true, &old_key_copied);
+ old_key_tuple = walLogical ?
+ ExtractReplicaIdentity(relation, &tp, true, &old_key_copied) : NULL;
/*
* If this is the first possibly-multixact-able operation in the current
@@ -3140,6 +3142,15 @@ l1:
xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
}
+ /*
+ * Unlike UPDATE, DELETE is decoded even if there is no old key, so it
+ * does not help to clear both XLH_DELETE_CONTAINS_OLD_TUPLE and
+ * XLH_DELETE_CONTAINS_OLD_KEY. Thus we need an extra flag. TODO
+ * Consider not decoding tuples w/o the old tuple/key instead.
+ */
+ if (!walLogical)
+ xlrec.flags |= XLH_DELETE_NO_LOGICAL;
+
XLogBeginInsert();
XLogRegisterData(&xlrec, SizeOfHeapDelete);
@@ -3232,7 +3243,8 @@ simple_heap_delete(Relation relation, const ItemPointerData *tid)
result = heap_delete(relation, tid,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
- &tmfd, false /* changingPart */ );
+ &tmfd, false, /* changingPart */
+ true /* walLogical */ );
switch (result)
{
case TM_SelfModified:
@@ -3273,7 +3285,7 @@ TM_Result
heap_update(Relation relation, const ItemPointerData *otid, HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
TM_FailureData *tmfd, LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes)
+ TU_UpdateIndexes *update_indexes, bool walLogical)
{
TM_Result result;
TransactionId xid = GetCurrentTransactionId();
@@ -4166,7 +4178,8 @@ l2:
newbuf, &oldtup, heaptup,
old_key_tuple,
all_visible_cleared,
- all_visible_cleared_new);
+ all_visible_cleared_new,
+ walLogical);
if (newbuf != buffer)
{
PageSetLSN(BufferGetPage(newbuf), recptr);
@@ -4524,7 +4537,8 @@ simple_heap_update(Relation relation, const ItemPointerData *otid, HeapTuple tup
result = heap_update(relation, otid, tup,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
- &tmfd, &lockmode, update_indexes);
+ &tmfd, &lockmode, update_indexes,
+ true /* walLogical */ );
switch (result)
{
case TM_SelfModified:
@@ -8864,7 +8878,8 @@ static XLogRecPtr
log_heap_update(Relation reln, Buffer oldbuf,
Buffer newbuf, HeapTuple oldtup, HeapTuple newtup,
HeapTuple old_key_tuple,
- bool all_visible_cleared, bool new_all_visible_cleared)
+ bool all_visible_cleared, bool new_all_visible_cleared,
+ bool walLogical)
{
xl_heap_update xlrec;
xl_heap_header xlhdr;
@@ -8875,7 +8890,8 @@ log_heap_update(Relation reln, Buffer oldbuf,
suffixlen = 0;
XLogRecPtr recptr;
Page page = BufferGetPage(newbuf);
- bool need_tuple_data = RelationIsLogicallyLogged(reln);
+ bool need_tuple_data = RelationIsLogicallyLogged(reln) &&
+ walLogical;
bool init;
int bufflags;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index b3a19003cdd..6063e037edb 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -33,6 +33,7 @@
#include "catalog/index.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
+#include "commands/cluster.h"
#include "commands/progress.h"
#include "executor/executor.h"
#include "miscadmin.h"
@@ -309,7 +310,8 @@ heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid,
* the storage itself is cleaning the dead tuples by itself, it is the
* time to call the index tuple deletion also.
*/
- return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart);
+ return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart,
+ true);
}
@@ -328,7 +330,7 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot,
tuple->t_tableOid = slot->tts_tableOid;
result = heap_update(relation, otid, tuple, cid, crosscheck, wait,
- tmfd, lockmode, update_indexes);
+ tmfd, lockmode, update_indexes, true);
ItemPointerCopy(&tuple->t_self, &slot->tts_tid);
/*
@@ -685,13 +687,15 @@ static void
heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
Relation OldIndex, bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
double *tups_recently_dead)
{
- RewriteState rwstate;
+ RewriteState rwstate = NULL;
IndexScanDesc indexScan;
TableScanDesc tableScan;
HeapScanDesc heapScan;
@@ -705,6 +709,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
bool *isnull;
BufferHeapTupleTableSlot *hslot;
BlockNumber prev_cblock = InvalidBlockNumber;
+ bool concurrent = snapshot != NULL;
+ XLogRecPtr end_of_wal_prev = GetFlushRecPtr(NULL);
/* Remember if it's a system catalog */
is_system_catalog = IsSystemRelation(OldHeap);
@@ -720,9 +726,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
values = palloc_array(Datum, natts);
isnull = palloc_array(bool, natts);
- /* Initialize the rewrite operation */
- rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff,
- *multi_cutoff);
+ /*
+ * Initialize the rewrite operation.
+ */
+ if (!concurrent)
+ rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
+ *xid_cutoff, *multi_cutoff);
/* Set up sorting if wanted */
@@ -737,6 +746,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* Prepare to scan the OldHeap. To ensure we see recently-dead tuples
* that still need to be copied, we scan with SnapshotAny and use
* HeapTupleSatisfiesVacuum for the visibility test.
+ *
+ * In the CONCURRENTLY case, we do regular MVCC visibility tests, using
+ * the snapshot passed by the caller.
*/
if (OldIndex != NULL && !use_sort)
{
@@ -753,7 +765,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
tableScan = NULL;
heapScan = NULL;
- indexScan = index_beginscan(OldHeap, OldIndex, SnapshotAny, NULL, 0, 0);
+ indexScan = index_beginscan(OldHeap, OldIndex,
+ snapshot ? snapshot : SnapshotAny,
+ NULL, 0, 0);
index_rescan(indexScan, NULL, 0, NULL, 0);
}
else
@@ -762,7 +776,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP);
- tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL);
+ tableScan = table_beginscan(OldHeap,
+ snapshot ? snapshot : SnapshotAny,
+ 0, (ScanKey) NULL);
heapScan = (HeapScanDesc) tableScan;
indexScan = NULL;
@@ -837,70 +853,77 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
tuple = ExecFetchSlotHeapTuple(slot, false, NULL);
buf = hslot->buffer;
- LockBuffer(buf, BUFFER_LOCK_SHARE);
-
- switch (HeapTupleSatisfiesVacuum(tuple, OldestXmin, buf))
+ /*
+ * Regarding CONCURRENTLY, see the comments on MVCC snapshot above.
+ */
+ if (!concurrent)
{
- case HEAPTUPLE_DEAD:
- /* Definitely dead */
- isdead = true;
- break;
- case HEAPTUPLE_RECENTLY_DEAD:
- *tups_recently_dead += 1;
- /* fall through */
- case HEAPTUPLE_LIVE:
- /* Live or recently dead, must copy it */
- isdead = false;
- break;
- case HEAPTUPLE_INSERT_IN_PROGRESS:
+ LockBuffer(buf, BUFFER_LOCK_SHARE);
- /*
- * Since we hold exclusive lock on the relation, normally the
- * only way to see this is if it was inserted earlier in our
- * own transaction. However, it can happen in system
- * catalogs, since we tend to release write lock before commit
- * there. Give a warning if neither case applies; but in any
- * case we had better copy it.
- */
- if (!is_system_catalog &&
- !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple->t_data)))
- elog(WARNING, "concurrent insert in progress within table \"%s\"",
- RelationGetRelationName(OldHeap));
- /* treat as live */
- isdead = false;
- break;
- case HEAPTUPLE_DELETE_IN_PROGRESS:
+ switch (HeapTupleSatisfiesVacuum(tuple, OldestXmin, buf))
+ {
+ case HEAPTUPLE_DEAD:
+ /* Definitely dead */
+ isdead = true;
+ break;
+ case HEAPTUPLE_RECENTLY_DEAD:
+ *tups_recently_dead += 1;
+ /* fall through */
+ case HEAPTUPLE_LIVE:
+ /* Live or recently dead, must copy it */
+ isdead = false;
+ break;
+ case HEAPTUPLE_INSERT_IN_PROGRESS:
- /*
- * Similar situation to INSERT_IN_PROGRESS case.
- */
- if (!is_system_catalog &&
- !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tuple->t_data)))
- elog(WARNING, "concurrent delete in progress within table \"%s\"",
- RelationGetRelationName(OldHeap));
- /* treat as recently dead */
- *tups_recently_dead += 1;
- isdead = false;
- break;
- default:
- elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
- isdead = false; /* keep compiler quiet */
- break;
- }
+ /*
+ * As long as we hold exclusive lock on the relation,
+ * normally the only way to see this is if it was inserted
+ * earlier in our own transaction. However, it can happen
+ * in system catalogs, since we tend to release write lock
+ * before commit there. Give a warning if neither case
+ * applies; but in any case we had better copy it.
+ */
+ if (!is_system_catalog &&
+ !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple->t_data)))
+ elog(WARNING, "concurrent insert in progress within table \"%s\"",
+ RelationGetRelationName(OldHeap));
+ /* treat as live */
+ isdead = false;
+ break;
+ case HEAPTUPLE_DELETE_IN_PROGRESS:
+
+ /*
+ * Similar situation to INSERT_IN_PROGRESS case.
+ */
+ if (!is_system_catalog &&
+ !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tuple->t_data)))
+ elog(WARNING, "concurrent delete in progress within table \"%s\"",
+ RelationGetRelationName(OldHeap));
+ /* treat as recently dead */
+ *tups_recently_dead += 1;
+ isdead = false;
+ break;
+ default:
+ elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
+ isdead = false; /* keep compiler quiet */
+ break;
+ }
- LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+ LockBuffer(buf, BUFFER_LOCK_UNLOCK);
- if (isdead)
- {
- *tups_vacuumed += 1;
- /* heap rewrite module still needs to see it... */
- if (rewrite_heap_dead_tuple(rwstate, tuple))
+ if (isdead)
{
- /* A previous recently-dead tuple is now known dead */
*tups_vacuumed += 1;
- *tups_recently_dead -= 1;
+ /* heap rewrite module still needs to see it... */
+ if (rewrite_heap_dead_tuple(rwstate, tuple))
+ {
+ /* A previous recently-dead tuple is now known dead */
+ *tups_vacuumed += 1;
+ *tups_recently_dead -= 1;
+ }
+
+ continue;
}
- continue;
}
*num_tuples += 1;
@@ -919,7 +942,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
{
const int ct_index[] = {
PROGRESS_REPACK_HEAP_TUPLES_SCANNED,
- PROGRESS_REPACK_HEAP_TUPLES_WRITTEN
+ PROGRESS_REPACK_HEAP_TUPLES_INSERTED
};
int64 ct_val[2];
@@ -934,6 +957,31 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
ct_val[1] = *num_tuples;
pgstat_progress_update_multi_param(2, ct_index, ct_val);
}
+
+ /*
+ * Process the WAL produced by the load, as well as by other
+ * transactions, so that the replication slot can advance and WAL does
+ * not pile up. Use wal_segment_size as a threshold so that we do not
+ * introduce the decoding overhead too often.
+ *
+ * Of course, we must not apply the changes until the initial load has
+ * completed.
+ *
+ * Note that our insertions into the new table should not be decoded
+ * as we (intentionally) do not write the logical decoding specific
+ * information to WAL.
+ */
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ end_of_wal = GetFlushRecPtr(NULL);
+ if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
+ {
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+ end_of_wal_prev = end_of_wal;
+ }
+ }
}
if (indexScan != NULL)
@@ -977,15 +1025,32 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
values, isnull,
rwstate);
/* Report n_tuples */
- pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_WRITTEN,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
n_tuples);
+
+ /*
+ * Try to keep the amount of not-yet-decoded WAL small, like
+ * above.
+ */
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ end_of_wal = GetFlushRecPtr(NULL);
+ if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
+ {
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+ end_of_wal_prev = end_of_wal;
+ }
+ }
}
tuplesort_end(tuplesort);
}
/* Write out any remaining tuples, and fsync if needed */
- end_heap_rewrite(rwstate);
+ if (rwstate)
+ end_heap_rewrite(rwstate);
/* Clean up */
pfree(values);
@@ -2376,6 +2441,10 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
* SET WITHOUT OIDS.
*
* So, we must reconstruct the tuple from component Datums.
+ *
+ * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
+ * case we still need to deform/form the tuple. TODO Shouldn't we rename the
+ * function, as might not do any rewrite?
*/
static void
reform_and_rewrite_tuple(HeapTuple tuple,
@@ -2398,8 +2467,28 @@ reform_and_rewrite_tuple(HeapTuple tuple,
copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
- /* The heap rewrite module does the rest */
- rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+ if (rwstate)
+ /* The heap rewrite module does the rest */
+ rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+ else
+ {
+ /*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * The following is like simple_heap_insert() except that we pass the
+ * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
+ * the relation files, it drops this relation, so no logical
+ * replication subscription should need the data.
+ */
+ heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
+ HEAP_INSERT_NO_LOGICAL, NULL);
+ }
heap_freetuple(copiedTuple);
}
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index 7ce3c5e2685..ef428486030 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -617,9 +617,9 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
int options = HEAP_INSERT_SKIP_FSM;
/*
- * While rewriting the heap for VACUUM FULL / CLUSTER, make sure data
- * for the TOAST table are not logically decoded. The main heap is
- * WAL-logged as XLOG FPI records, which are not logically decoded.
+ * While rewriting the heap for REPACK, make sure data for the TOAST
+ * table are not logically decoded. The main heap is WAL-logged as
+ * XLOG FPI records, which are not logically decoded.
*/
options |= HEAP_INSERT_NO_LOGICAL;
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 6c1461c9ef6..9b7f8cf8497 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1298,16 +1298,19 @@ CREATE VIEW pg_stat_progress_repack AS
WHEN 2 THEN 'index scanning heap'
WHEN 3 THEN 'sorting tuples'
WHEN 4 THEN 'writing new heap'
- WHEN 5 THEN 'swapping relation files'
- WHEN 6 THEN 'rebuilding index'
- WHEN 7 THEN 'performing final cleanup'
+ WHEN 5 THEN 'catch-up'
+ WHEN 6 THEN 'swapping relation files'
+ WHEN 7 THEN 'rebuilding index'
+ WHEN 8 THEN 'performing final cleanup'
END AS phase,
CAST(S.param3 AS oid) AS repack_index_relid,
S.param4 AS heap_tuples_scanned,
- S.param5 AS heap_tuples_written,
- S.param6 AS heap_blks_total,
- S.param7 AS heap_blks_scanned,
- S.param8 AS index_rebuild_count
+ S.param5 AS heap_tuples_inserted,
+ S.param6 AS heap_tuples_updated,
+ S.param7 AS heap_tuples_deleted,
+ S.param8 AS heap_blks_total,
+ S.param9 AS heap_blks_scanned,
+ S.param10 AS index_rebuild_count
FROM pg_stat_get_progress_info('REPACK') AS S
LEFT JOIN pg_database D ON S.datid = D.oid;
@@ -1325,7 +1328,7 @@ CREATE VIEW pg_stat_progress_cluster AS
phase,
repack_index_relid AS cluster_index_relid,
heap_tuples_scanned,
- heap_tuples_written,
+ heap_tuples_inserted + heap_tuples_updated AS heap_tuples_written,
heap_blks_total,
heap_blks_scanned,
index_rebuild_count
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index a2d72ce494d..569705abc81 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1,8 +1,23 @@
/*-------------------------------------------------------------------------
*
* cluster.c
- * CLUSTER a table on an index. This is now also used for VACUUM FULL and
- * REPACK.
+ * Implementation of REPACK [CONCURRENTLY], also known as CLUSTER and
+ * VACUUM FULL.
+ *
+ * There are two somewhat different ways to rewrite a table. In non-
+ * concurrent mode, it's easy: take AccessExclusiveLock, create a new
+ * transient relation, copy the tuples over to the relfilenode of the new
+ * relation, swap the relfilenodes, then drop the old relation.
+ *
+ * In concurrent mode, we lock the table with only ShareUpdateExclusiveLock,
+ * then do an initial copy as above. However, while the tuples are being
+ * copied, concurrent transactions could modify the table. To cope with those
+ * changes, we rely on logical decoding to obtain them from WAL. The changes
+ * are accumulated in a tuplestore. Once the initial copy is complete, we
+ * read the changes from the tuplestore and re-apply them on the new heap.
+ * Then we upgrade our ShareUpdateExclusiveLock to AccessExclusiveLock and
+ * swap the relfilenodes. This way, the time we hold a strong lock on the
+ * table is much reduced, and the bloat is eliminated.
*
* There is hardly anything left of Paul Brown's original implementation...
*
@@ -26,6 +41,10 @@
#include "access/toast_internals.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xlog_internal.h"
+#include "access/xloginsert.h"
+#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/heap.h"
@@ -33,6 +52,7 @@
#include "catalog/namespace.h"
#include "catalog/objectaccess.h"
#include "catalog/pg_am.h"
+#include "catalog/pg_control.h"
#include "catalog/pg_inherits.h"
#include "catalog/toasting.h"
#include "commands/cluster.h"
@@ -40,15 +60,21 @@
#include "commands/progress.h"
#include "commands/tablecmds.h"
#include "commands/vacuum.h"
+#include "executor/executor.h"
#include "miscadmin.h"
#include "optimizer/optimizer.h"
#include "pgstat.h"
+#include "replication/decode.h"
+#include "replication/logical.h"
+#include "replication/snapbuild.h"
#include "storage/bufmgr.h"
+#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "utils/acl.h"
#include "utils/fmgroids.h"
#include "utils/guc.h"
+#include "utils/injection_point.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
@@ -68,12 +94,62 @@ typedef struct
Oid indexOid;
} RelToCluster;
+/*
+ * The following definitions are used for concurrent processing.
+ */
+
+/*
+ * The locators are used to avoid logical decoding of data that we do not need
+ * for our table.
+ */
+RelFileLocator repacked_rel_locator = {.relNumber = InvalidOid};
+RelFileLocator repacked_rel_toast_locator = {.relNumber = InvalidOid};
+
+/*
+ * Everything we need to call ExecInsertIndexTuples().
+ */
+typedef struct IndexInsertState
+{
+ ResultRelInfo *rri;
+ EState *estate;
+} IndexInsertState;
+
+/* The WAL segment being decoded. */
+static XLogSegNo repack_current_segment = 0;
+
+/*
+ * Information needed to apply concurrent data changes.
+ */
+typedef struct ChangeDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ /*
+ * The following is needed to find the existing tuple if the change is
+ * UPDATE or DELETE. 'ident_key' should have all the fields except for
+ * 'sk_argument' initialized.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+ int ident_key_nentries;
+
+ /* Needed to update indexes of rel_dst. */
+ IndexInsertState *iistate;
+} ChangeDest;
+
static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap,
- Oid indexOid, Oid userid, int options);
-static void rebuild_relation(Relation OldHeap, Relation index, bool verbose);
+ Oid indexOid, Oid userid, LOCKMODE lmode,
+ int options);
+static void check_repack_concurrently_requirements(Relation rel);
+static void rebuild_relation(Relation OldHeap, Relation index, bool verbose,
+ bool concurrent);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- bool verbose, bool *pSwapToastByContent,
- TransactionId *pFreezeXid, MultiXactId *pCutoffMulti);
+ Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
+ bool verbose,
+ bool *pSwapToastByContent,
+ TransactionId *pFreezeXid,
+ MultiXactId *pCutoffMulti);
static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
MemoryContext permcxt);
static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -81,13 +157,51 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
MemoryContext permcxt);
static bool cluster_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
+
+static void begin_concurrent_repack(Relation rel);
+static void end_concurrent_repack(void);
+static LogicalDecodingContext *setup_logical_decoding(Oid relid);
+static HeapTuple get_changed_tuple(char *change);
+static void apply_concurrent_changes(RepackDecodingState *dstate,
+ ChangeDest *dest);
+static void apply_concurrent_insert(Relation rel, HeapTuple tup,
+ IndexInsertState *iistate,
+ TupleTableSlot *index_slot);
+static void apply_concurrent_update(Relation rel, HeapTuple tup,
+ HeapTuple tup_target,
+ IndexInsertState *iistate,
+ TupleTableSlot *index_slot);
+static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
+static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
+ HeapTuple tup_key,
+ TupleTableSlot *ident_slot);
+static void process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
+ XLogRecPtr end_of_wal,
+ ChangeDest *dest);
+static IndexInsertState *get_index_insert_state(Relation relation,
+ Oid ident_index_id,
+ Relation *ident_index_p);
+static ScanKey build_identity_key(Oid ident_idx_oid, Relation rel_src,
+ int *nentries);
+static void free_index_insert_state(IndexInsertState *iistate);
+static void cleanup_logical_decoding(LogicalDecodingContext *ctx);
+static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
+ Relation cl_index,
+ LogicalDecodingContext *decoding_ctx,
+ TransactionId frozenXid,
+ MultiXactId cutoffMulti);
+static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes);
static Relation process_single_relation(RepackStmt *stmt,
+ LOCKMODE lockmode,
+ bool isTopLevel,
ClusterParams *params);
static Oid determine_clustered_index(Relation rel, bool usingindex,
const char *indexname);
static const char *RepackCommandAsString(RepackCommand cmd);
+#define REPL_PLUGIN_NAME "pgoutput_repack"
+
/*
* The repack code allows for processing multiple tables at once. Because
* of this, we cannot just run everything on a single transaction, or we
@@ -117,6 +231,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
ClusterParams params = {0};
Relation rel = NULL;
MemoryContext repack_context;
+ LOCKMODE lockmode;
List *rtcs;
/* Parse option list */
@@ -127,6 +242,16 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
else if (strcmp(opt->defname, "analyze") == 0 ||
strcmp(opt->defname, "analyse") == 0)
params.options |= defGetBoolean(opt) ? CLUOPT_ANALYZE : 0;
+ else if (strcmp(opt->defname, "concurrently") == 0 &&
+ defGetBoolean(opt))
+ {
+ if (stmt->command != REPACK_COMMAND_REPACK)
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("CONCURRENTLY option not supported for %s",
+ RepackCommandAsString(stmt->command)));
+ params.options |= CLUOPT_CONCURRENT;
+ }
else
ereport(ERROR,
errcode(ERRCODE_SYNTAX_ERROR),
@@ -136,13 +261,25 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
parser_errposition(pstate, opt->location));
}
+ /*
+ * Determine the lock mode expected by cluster_rel().
+ *
+ * In the exclusive case, we obtain AccessExclusiveLock right away to
+ * avoid lock-upgrade hazard in the single-transaction case. In the
+ * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end
+ * of processing, supposedly for very short time. Until then, we'll have
+ * to unlock the relation temporarily, so there's no lock-upgrade hazard.
+ */
+ lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ?
+ AccessExclusiveLock : ShareUpdateExclusiveLock;
+
/*
* 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.
*/
if (stmt->relation != NULL)
{
- rel = process_single_relation(stmt, ¶ms);
+ rel = process_single_relation(stmt, lockmode, isTopLevel, ¶ms);
if (rel == NULL)
return; /* all done */
}
@@ -157,10 +294,29 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
errmsg("cannot %s multiple tables", "REPACK (ANALYZE)"));
/*
- * By here, we know we are in a multi-table situation. In order to avoid
- * holding locks for too long, we want to process each table in its own
- * transaction. This forces us to disallow running inside a user
- * transaction block.
+ * By here, we know we are in a multi-table situation.
+ *
+ * Concurrent processing is currently considered rather special (e.g. in
+ * terms of resources consumed) so it is not performed in bulk.
+ */
+ if (params.options & CLUOPT_CONCURRENT)
+ {
+ if (rel != NULL)
+ {
+ Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
+ ereport(ERROR,
+ errmsg("REPACK CONCURRENTLY not supported for partitioned tables"),
+ errhint("Consider running the command for individual partitions."));
+ }
+ else
+ ereport(ERROR,
+ errmsg("REPACK CONCURRENTLY requires explicit table name"));
+ }
+
+ /*
+ * In order to avoid holding locks for too long, we want to process each
+ * table in its own transaction. This forces us to disallow running
+ * inside a user transaction block.
*/
PreventInTransactionBlock(isTopLevel, RepackCommandAsString(stmt->command));
@@ -243,7 +399,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
* Open the target table, coping with the case where it has been
* dropped.
*/
- rel = try_table_open(rtc->tableOid, AccessExclusiveLock);
+ rel = try_table_open(rtc->tableOid, lockmode);
if (rel == NULL)
{
CommitTransactionCommand();
@@ -254,7 +410,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
PushActiveSnapshot(GetTransactionSnapshot());
/* Process this table */
- cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms);
+ cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms, isTopLevel);
/* cluster_rel closes the relation, but keeps lock */
PopActiveSnapshot();
@@ -283,22 +439,53 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
* 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.)
+ *
* 'cmd' indicates which command is being executed, to be used for error
* messages.
*/
void
cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
- ClusterParams *params)
+ ClusterParams *params, bool isTopLevel)
{
Oid tableOid = RelationGetRelid(OldHeap);
+ Relation index;
+ LOCKMODE lmode;
Oid save_userid;
int save_sec_context;
int save_nestlevel;
bool verbose = ((params->options & CLUOPT_VERBOSE) != 0);
bool recheck = ((params->options & CLUOPT_RECHECK) != 0);
- Relation index;
+ bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0);
+
+ /*
+ * The lock mode is AccessExclusiveLock for normal processing and
+ * ShareUpdateExclusiveLock for concurrent processing (so that SELECT,
+ * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be
+ * called concurrently for the same relation).
+ */
+ lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock;
- Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false));
+ /* There are specific requirements on concurrent processing. */
+ if (concurrent)
+ {
+ /*
+ * Make sure we have no XID assigned, otherwise call of
+ * setup_logical_decoding() can cause a deadlock.
+ *
+ * The existence of transaction block actually does not imply that XID
+ * was already assigned, but it very likely is. We might want to check
+ * the result of GetCurrentTransactionIdIfAny() instead, but that
+ * would be less clear from user's perspective.
+ */
+ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)");
+
+ check_repack_concurrently_requirements(OldHeap);
+ }
/* Check for user-requested abort. */
CHECK_FOR_INTERRUPTS();
@@ -324,10 +511,13 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* If this is a single-transaction CLUSTER, we can skip these tests. We
* *must* skip the one on indisclustered since it would reject an attempt
* to cluster a not-previously-clustered index.
+ *
+ * XXX move [some of] these comments to where the RECHECK flag is
+ * determined?
*/
if (recheck &&
!cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid,
- params->options))
+ lmode, params->options))
goto out;
/*
@@ -342,6 +532,12 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
errmsg("cannot run %s on a shared catalog",
RepackCommandAsString(cmd)));
+ /*
+ * The CONCURRENTLY case should have been rejected earlier because it does
+ * not support system catalogs.
+ */
+ Assert(!(OldHeap->rd_rel->relisshared && concurrent));
+
/*
* Don't process temp tables of other backends ... their local buffer
* manager is not going to cope.
@@ -362,7 +558,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if (OidIsValid(indexOid))
{
/* verify the index is good and lock it */
- check_index_is_clusterable(OldHeap, indexOid, AccessExclusiveLock);
+ check_index_is_clusterable(OldHeap, indexOid, lmode);
/* also open it */
index = index_open(indexOid, NoLock);
}
@@ -397,7 +593,9 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if (OldHeap->rd_rel->relkind == RELKIND_MATVIEW &&
!RelationIsPopulated(OldHeap))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ if (index)
+ index_close(index, lmode);
+ relation_close(OldHeap, lmode);
goto out;
}
@@ -410,11 +608,34 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* invalid, because we move tuples around. Promote them to relation
* locks. Predicate locks on indexes will be promoted when they are
* reindexed.
+ *
+ * During concurrent processing, the heap as well as its indexes stay in
+ * operation, so we postpone this step until they are locked using
+ * AccessExclusiveLock near the end of the processing.
*/
- TransferPredicateLocksToHeapRelation(OldHeap);
+ if (!concurrent)
+ TransferPredicateLocksToHeapRelation(OldHeap);
/* rebuild_relation does all the dirty work */
- rebuild_relation(OldHeap, index, verbose);
+ PG_TRY();
+ {
+ /*
+ * For concurrent processing, make sure that our logical decoding
+ * ignores data changes of other tables than the one we are
+ * processing.
+ */
+ if (concurrent)
+ begin_concurrent_repack(OldHeap);
+
+ rebuild_relation(OldHeap, index, verbose, concurrent);
+ }
+ PG_FINALLY();
+ {
+ if (concurrent)
+ end_concurrent_repack();
+ }
+ PG_END_TRY();
+
/* rebuild_relation closes OldHeap, and index if valid */
out:
@@ -433,14 +654,14 @@ out:
*/
static bool
cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
- Oid userid, int options)
+ Oid userid, LOCKMODE lmode, int options)
{
Oid tableOid = RelationGetRelid(OldHeap);
/* Check that the user still has privileges for the relation */
if (!cluster_is_permitted_for_relation(cmd, tableOid, userid))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -454,7 +675,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
*/
if (RELATION_IS_OTHER_TEMP(OldHeap))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -465,7 +686,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
*/
if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid)))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -476,7 +697,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if ((options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
!get_index_isclustered(indexOid))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
}
@@ -488,7 +709,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* Verify that the specified heap and index are valid to cluster on
*
* Side effect: obtains lock on the index. The caller may
- * in some cases already have AccessExclusiveLock on the table, but
+ * in some cases already have a lock of the same strength on the table, but
* not in all cases so we can't rely on the table-level lock for
* protection here.
*/
@@ -617,18 +838,87 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
table_close(pg_index, RowExclusiveLock);
}
+/*
+ * Check if the CONCURRENTLY option is legal for the relation.
+ */
+static void
+check_repack_concurrently_requirements(Relation rel)
+{
+ char relpersistence,
+ replident;
+ Oid ident_idx;
+
+ /* Data changes in system relations are not logically decoded. */
+ if (IsCatalogRelation(rel))
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is not supported for catalog relations.")));
+
+ /*
+ * reorderbuffer.c does not seem to handle processing of TOAST relation
+ * alone.
+ */
+ if (IsToastRelation(rel))
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is not supported for TOAST relations, unless the main relation is repacked too.")));
+
+ relpersistence = rel->rd_rel->relpersistence;
+ if (relpersistence != RELPERSISTENCE_PERMANENT)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is only allowed for permanent relations.")));
+
+ /* With NOTHING, WAL does not contain the old tuple. */
+ replident = rel->rd_rel->relreplident;
+ if (replident == REPLICA_IDENTITY_NOTHING)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("Relation \"%s\" has insufficient replication identity.",
+ RelationGetRelationName(rel))));
+
+ /*
+ * Identity index is not set if the replica identity is FULL, but PK might
+ * exist in such a case.
+ */
+ ident_idx = RelationGetReplicaIndex(rel);
+ if (!OidIsValid(ident_idx) && OidIsValid(rel->rd_pkindex))
+ ident_idx = rel->rd_pkindex;
+ if (!OidIsValid(ident_idx))
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot process relation \"%s\"",
+ RelationGetRelationName(rel)),
+ (errhint("Relation \"%s\" has no identity index.",
+ RelationGetRelationName(rel)))));
+}
+
+
/*
* rebuild_relation: rebuild an existing relation in index or physical order
*
- * OldHeap: table to rebuild.
+ * OldHeap: table to rebuild. See cluster_rel() for comments on the required
+ * lock strength.
+ *
* index: index to cluster by, or NULL to rewrite in physical order.
*
- * On entry, heap and index (if one is given) must be open, and
- * AccessExclusiveLock held on them.
- * On exit, they are closed, but locks on them are not released.
+ * On entry, heap and index (if one is given) must be open, and the
+ * appropriate lock held on them -- AccessExclusiveLock for exclusive
+ * processing and ShareUpdateExclusiveLock for concurrent processing.
+ *
+ * On exit, they are closed, but still locked with AccessExclusiveLock.
+ * (The function handles the lock upgrade if 'concurrent' is true.)
*/
static void
-rebuild_relation(Relation OldHeap, Relation index, bool verbose)
+rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent)
{
Oid tableOid = RelationGetRelid(OldHeap);
Oid accessMethod = OldHeap->rd_rel->relam;
@@ -636,13 +926,38 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
Oid OIDNewHeap;
Relation NewHeap;
char relpersistence;
- bool is_system_catalog;
bool swap_toast_by_content;
TransactionId frozenXid;
MultiXactId cutoffMulti;
+ LogicalDecodingContext *decoding_ctx = NULL;
+ Snapshot snapshot = NULL;
+#if USE_ASSERT_CHECKING
+ LOCKMODE lmode;
+
+ lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
+
+ Assert(CheckRelationLockedByMe(OldHeap, lmode, false));
+ Assert(index == NULL || CheckRelationLockedByMe(index, lmode, false));
+#endif
+
+ if (concurrent)
+ {
+ /*
+ * Prepare to capture the concurrent data changes.
+ *
+ * Note that this call waits 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 its still eligible for REPACK
+ * CONCURRENTLY.
+ */
+ decoding_ctx = setup_logical_decoding(tableOid);
- Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false) &&
- (index == NULL || CheckRelationLockedByMe(index, AccessExclusiveLock, false)));
+ snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
+ PushActiveSnapshot(snapshot);
+ }
/* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */
if (index != NULL)
@@ -650,7 +965,6 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
/* Remember info about rel before closing OldHeap */
relpersistence = OldHeap->rd_rel->relpersistence;
- is_system_catalog = IsSystemRelation(OldHeap);
/*
* Create the transient table that will receive the re-ordered data.
@@ -666,30 +980,54 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
NewHeap = table_open(OIDNewHeap, NoLock);
/* Copy the heap data into the new table in the desired order */
- copy_table_data(NewHeap, OldHeap, index, verbose,
+ copy_table_data(NewHeap, OldHeap, index, snapshot, decoding_ctx, verbose,
&swap_toast_by_content, &frozenXid, &cutoffMulti);
+ /* The historic snapshot won't be needed anymore. */
+ if (snapshot)
+ {
+ PopActiveSnapshot();
+ UpdateActiveSnapshotCommandId();
+ }
- /* Close relcache entries, but keep lock until transaction commit */
- table_close(OldHeap, NoLock);
- if (index)
- index_close(index, NoLock);
+ if (concurrent)
+ {
+ Assert(!swap_toast_by_content);
+ rebuild_relation_finish_concurrent(NewHeap, OldHeap, index,
+ decoding_ctx,
+ frozenXid, cutoffMulti);
- /*
- * Close the new relation so it can be dropped as soon as the storage is
- * swapped. The relation is not visible to others, so no need to unlock it
- * explicitly.
- */
- table_close(NewHeap, NoLock);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
- /*
- * Swap the physical files of the target and transient tables, then
- * rebuild the target's indexes and throw away the transient table.
- */
- finish_heap_swap(tableOid, OIDNewHeap, is_system_catalog,
- swap_toast_by_content, false, true,
- frozenXid, cutoffMulti,
- relpersistence);
+ /* Done with decoding. */
+ cleanup_logical_decoding(decoding_ctx);
+ }
+ else
+ {
+ bool is_system_catalog = IsSystemRelation(OldHeap);
+
+ /* Close relcache entries, but keep lock until transaction commit */
+ table_close(OldHeap, NoLock);
+ if (index)
+ index_close(index, NoLock);
+
+ /*
+ * Close the new relation so it can be dropped as soon as the storage
+ * is swapped. The relation is not visible to others, so no need to
+ * unlock it explicitly.
+ */
+ table_close(NewHeap, NoLock);
+
+ /*
+ * Swap the physical files of the target and transient tables, then
+ * rebuild the target's indexes and throw away the transient table.
+ */
+ finish_heap_swap(tableOid, OIDNewHeap, is_system_catalog,
+ swap_toast_by_content, false, true, true,
+ frozenXid, cutoffMulti,
+ relpersistence);
+ }
}
@@ -824,15 +1162,19 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
/*
* Do the physical copying of table data.
*
+ * 'snapshot' and 'decoding_ctx': see table_relation_copy_for_cluster(). Pass
+ * iff concurrent processing is required.
+ *
* There are three output parameters:
* *pSwapToastByContent is set true if toast tables must be swapped by content.
* *pFreezeXid receives the TransactionId used as freeze cutoff point.
* *pCutoffMulti receives the MultiXactId used as a cutoff point.
*/
static void
-copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verbose,
- bool *pSwapToastByContent, TransactionId *pFreezeXid,
- MultiXactId *pCutoffMulti)
+copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
+ Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
+ bool verbose, bool *pSwapToastByContent,
+ TransactionId *pFreezeXid, MultiXactId *pCutoffMulti)
{
Relation relRelation;
HeapTuple reltup;
@@ -849,6 +1191,10 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
int elevel = verbose ? INFO : DEBUG2;
PGRUsage ru0;
char *nspname;
+ bool concurrent = snapshot != NULL;
+ LOCKMODE lmode;
+
+ lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
pg_rusage_init(&ru0);
@@ -877,7 +1223,7 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* will be held till end of transaction.
*/
if (OldHeap->rd_rel->reltoastrelid)
- LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, lmode);
/*
* If both tables have TOAST tables, perform toast swap by content. It is
@@ -886,7 +1232,8 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* swap by links. This is okay because swap by content is only essential
* for system catalogs, and we don't support schema changes for them.
*/
- if (OldHeap->rd_rel->reltoastrelid && NewHeap->rd_rel->reltoastrelid)
+ if (OldHeap->rd_rel->reltoastrelid && NewHeap->rd_rel->reltoastrelid &&
+ !concurrent)
{
*pSwapToastByContent = true;
@@ -907,6 +1254,10 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* follow the toast pointers to the wrong place. (It would actually
* work for values copied over from the old toast table, but not for
* any values that we toast which were previously not toasted.)
+ *
+ * This would not work with CONCURRENTLY because we may need to delete
+ * TOASTed tuples from the new heap. With this hack, we'd delete them
+ * from the old heap.
*/
NewHeap->rd_toastoid = OldHeap->rd_rel->reltoastrelid;
}
@@ -982,7 +1333,9 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* values (e.g. because the AM doesn't use freezing).
*/
table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort,
- cutoffs.OldestXmin, &cutoffs.FreezeLimit,
+ cutoffs.OldestXmin, snapshot,
+ decoding_ctx,
+ &cutoffs.FreezeLimit,
&cutoffs.MultiXactCutoff,
&num_tuples, &tups_vacuumed,
&tups_recently_dead);
@@ -991,7 +1344,11 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
*pFreezeXid = cutoffs.FreezeLimit;
*pCutoffMulti = cutoffs.MultiXactCutoff;
- /* Reset rd_toastoid just to be tidy --- it shouldn't be looked at again */
+ /*
+ * Reset rd_toastoid just to be tidy --- it shouldn't be looked at again.
+ * In the CONCURRENTLY case, we need to set it again before applying the
+ * concurrent changes.
+ */
NewHeap->rd_toastoid = InvalidOid;
num_pages = RelationGetNumberOfBlocks(NewHeap);
@@ -1449,14 +1806,13 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
bool swap_toast_by_content,
bool check_constraints,
bool is_internal,
+ bool reindex,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence)
{
ObjectAddress object;
Oid mapped_tables[4];
- int reindex_flags;
- ReindexParams reindex_params = {0};
int i;
/* Report that we are now swapping relation files */
@@ -1482,39 +1838,47 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
if (is_system_catalog)
CacheInvalidateCatalog(OIDOldHeap);
- /*
- * Rebuild each index on the relation (but not the toast table, which is
- * all-new at this point). It is important to do this before the DROP
- * step because if we are processing a system catalog that will be used
- * during DROP, we want to have its indexes available. There is no
- * advantage to the other order anyway because this is all transactional,
- * so no chance to reclaim disk space before commit. We do not need a
- * final CommandCounterIncrement() because reindex_relation does it.
- *
- * Note: because index_build is called via reindex_relation, it will never
- * set indcheckxmin true for the indexes. This is OK even though in some
- * sense we are building new indexes rather than rebuilding existing ones,
- * because the new heap won't contain any HOT chains at all, let alone
- * broken ones, so it can't be necessary to set indcheckxmin.
- */
- reindex_flags = REINDEX_REL_SUPPRESS_INDEX_USE;
- if (check_constraints)
- reindex_flags |= REINDEX_REL_CHECK_CONSTRAINTS;
+ if (reindex)
+ {
+ int reindex_flags;
+ ReindexParams reindex_params = {0};
- /*
- * Ensure that the indexes have the same persistence as the parent
- * relation.
- */
- if (newrelpersistence == RELPERSISTENCE_UNLOGGED)
- reindex_flags |= REINDEX_REL_FORCE_INDEXES_UNLOGGED;
- else if (newrelpersistence == RELPERSISTENCE_PERMANENT)
- reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
+ /*
+ * Rebuild each index on the relation (but not the toast table, which
+ * is all-new at this point). It is important to do this before the
+ * DROP step because if we are processing a system catalog that will
+ * be used during DROP, we want to have its indexes available. There
+ * is no advantage to the other order anyway because this is all
+ * transactional, so no chance to reclaim disk space before commit. We
+ * do not need a final CommandCounterIncrement() because
+ * reindex_relation does it.
+ *
+ * Note: because index_build is called via reindex_relation, it will
+ * never set indcheckxmin true for the indexes. This is OK even
+ * though in some sense we are building new indexes rather than
+ * rebuilding existing ones, because the new heap won't contain any
+ * HOT chains at all, let alone broken ones, so it can't be necessary
+ * to set indcheckxmin.
+ */
+ reindex_flags = REINDEX_REL_SUPPRESS_INDEX_USE;
+ if (check_constraints)
+ reindex_flags |= REINDEX_REL_CHECK_CONSTRAINTS;
- /* Report that we are now reindexing relations */
- pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
- PROGRESS_REPACK_PHASE_REBUILD_INDEX);
+ /*
+ * Ensure that the indexes have the same persistence as the parent
+ * relation.
+ */
+ if (newrelpersistence == RELPERSISTENCE_UNLOGGED)
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_UNLOGGED;
+ else if (newrelpersistence == RELPERSISTENCE_PERMANENT)
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
+
+ /* Report that we are now reindexing relations */
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_REBUILD_INDEX);
- reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params);
+ reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params);
+ }
/* Report that we are now doing clean up */
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
@@ -1558,6 +1922,17 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
object.objectId = OIDNewHeap;
object.objectSubId = 0;
+ if (!reindex)
+ {
+ /*
+ * Make sure the changes in pg_class are visible. This is especially
+ * important if !swap_toast_by_content, so that the correct TOAST
+ * relation is dropped. (reindex_relation() above did not help in this
+ * case))
+ */
+ CommandCounterIncrement();
+ }
+
/*
* The new relation is local to our transaction and we know nothing
* depends on it, so DROP_RESTRICT should be OK.
@@ -1597,7 +1972,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
/* Get the associated valid index to be renamed */
toastidx = toast_get_valid_index(newrel->rd_rel->reltoastrelid,
- NoLock);
+ AccessExclusiveLock);
/* rename the toast table ... */
snprintf(NewToastName, NAMEDATALEN, "pg_toast_%u",
@@ -1857,7 +2232,8 @@ cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid)
* case, if an index name is given, it's up to the caller to resolve it.
*/
static Relation
-process_single_relation(RepackStmt *stmt, ClusterParams *params)
+process_single_relation(RepackStmt *stmt, LOCKMODE lockmode, bool isTopLevel,
+ ClusterParams *params)
{
Relation rel;
Oid tableOid;
@@ -1866,13 +2242,9 @@ process_single_relation(RepackStmt *stmt, ClusterParams *params)
Assert(stmt->command == REPACK_COMMAND_CLUSTER ||
stmt->command == REPACK_COMMAND_REPACK);
- /*
- * Find, lock, and check permissions on the table. We obtain
- * AccessExclusiveLock right away to avoid lock-upgrade hazard in the
- * single-transaction case.
- */
+ /* Find, lock, and check permissions on the table. */
tableOid = RangeVarGetRelidExtended(stmt->relation->relation,
- AccessExclusiveLock,
+ lockmode,
0,
RangeVarCallbackMaintainsTable,
NULL);
@@ -1904,13 +2276,14 @@ process_single_relation(RepackStmt *stmt, ClusterParams *params)
return rel;
else
{
- Oid indexOid;
+ Oid indexOid = InvalidOid;
indexOid = determine_clustered_index(rel, stmt->usingindex,
stmt->indexname);
if (OidIsValid(indexOid))
- check_index_is_clusterable(rel, indexOid, AccessExclusiveLock);
- cluster_rel(stmt->command, rel, indexOid, params);
+ check_index_is_clusterable(rel, indexOid, lockmode);
+
+ cluster_rel(stmt->command, rel, indexOid, params, isTopLevel);
/* Do an analyze, if requested */
if (params->options & CLUOPT_ANALYZE)
@@ -1993,3 +2366,1019 @@ RepackCommandAsString(RepackCommand cmd)
}
return "???";
}
+
+
+/*
+ * Call this function before REPACK CONCURRENTLY starts to setup logical
+ * decoding. It makes sure that other users of the table put enough
+ * information into WAL.
+ *
+ * The point is that at various places we expect that the table we're
+ * processing is treated like a system catalog. For example, we need to be
+ * able to scan it using a "historic snapshot" anytime during the processing
+ * (as opposed to scanning only at the start point of the decoding, as logical
+ * replication does during initial table synchronization), in order to apply
+ * concurrent UPDATE / DELETE commands.
+ *
+ * Note that TOAST table needs no attention here as it's not scanned using
+ * historic snapshot.
+ */
+static void
+begin_concurrent_repack(Relation rel)
+{
+ Oid toastrelid;
+
+ /*
+ * Avoid logical decoding of other relations by this backend. The lock we
+ * have guarantees that the actual locator cannot be changed concurrently:
+ * TRUNCATE needs AccessExclusiveLock.
+ */
+ Assert(CheckRelationLockedByMe(rel, ShareUpdateExclusiveLock, false));
+ repacked_rel_locator = rel->rd_locator;
+ toastrelid = rel->rd_rel->reltoastrelid;
+ if (OidIsValid(toastrelid))
+ {
+ Relation toastrel;
+
+ /* Avoid logical decoding of other TOAST relations. */
+ toastrel = table_open(toastrelid, AccessShareLock);
+ repacked_rel_toast_locator = toastrel->rd_locator;
+ table_close(toastrel, AccessShareLock);
+ }
+}
+
+/*
+ * Call this when done with REPACK CONCURRENTLY.
+ */
+static void
+end_concurrent_repack(void)
+{
+ /*
+ * Restore normal function of (future) logical decoding for this backend.
+ */
+ repacked_rel_locator.relNumber = InvalidOid;
+ repacked_rel_toast_locator.relNumber = InvalidOid;
+}
+
+/*
+ * This function is much like pg_create_logical_replication_slot() except that
+ * the new slot is neither released (if anyone else could read changes from
+ * our slot, we could miss changes other backends do while we copy the
+ * existing data into temporary table), nor persisted (it's easier to handle
+ * crash by restarting all the work from scratch).
+ */
+static LogicalDecodingContext *
+setup_logical_decoding(Oid relid)
+{
+ Relation rel;
+ TupleDesc tupdesc;
+ LogicalDecodingContext *ctx;
+ RepackDecodingState *dstate = palloc0_object(RepackDecodingState);
+
+ /*
+ * REPACK CONCURRENTLY is not allowed in a transaction block, so this
+ * should never fire.
+ */
+ Assert(!TransactionIdIsValid(GetTopTransactionIdIfAny()));
+
+ /*
+ * A single backend should not execute multiple REPACK commands at a time,
+ * so use PID to make the slot unique.
+ */
+ snprintf(NameStr(dstate->slotname), NAMEDATALEN, "repack_%d", MyProcPid);
+
+ /*
+ * Check if we can use logical decoding.
+ */
+ CheckSlotPermissions();
+ CheckLogicalDecodingRequirements();
+
+ /* RS_TEMPORARY so that the slot gets cleaned up on ERROR. */
+ ReplicationSlotCreate(NameStr(dstate->slotname), true, RS_TEMPORARY,
+ false, false, false);
+
+ /*
+ * Neither prepare_write nor do_write callback nor update_progress is
+ * useful for us.
+ */
+ ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME,
+ NIL,
+ true,
+ InvalidXLogRecPtr,
+ XL_ROUTINE(.page_read = read_local_xlog_page,
+ .segment_open = wal_segment_open,
+ .segment_close = wal_segment_close),
+ NULL, NULL, NULL);
+
+ /*
+ * We don't have control on setting fast_forward, so at least check it.
+ */
+ Assert(!ctx->fast_forward);
+
+ DecodingContextFindStartpoint(ctx);
+
+ /* Some WAL records should have been read. */
+ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr);
+
+ XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment,
+ wal_segment_size);
+
+ /*
+ * Setup structures to store decoded changes.
+ */
+ dstate->relid = relid;
+ dstate->tstore = tuplestore_begin_heap(false, false,
+ maintenance_work_mem);
+
+ /* Caller should already have the table locked. */
+ rel = table_open(relid, NoLock);
+ tupdesc = CreateTupleDescCopy(RelationGetDescr(rel));
+ dstate->tupdesc = tupdesc;
+ table_close(rel, NoLock);
+
+ /* Initialize the descriptor to store the changes ... */
+ dstate->tupdesc_change = CreateTemplateTupleDesc(1);
+
+ TupleDescInitEntry(dstate->tupdesc_change, 1, NULL, BYTEAOID, -1, 0);
+ /* ... as well as the corresponding slot. */
+ dstate->tsslot = MakeSingleTupleTableSlot(dstate->tupdesc_change,
+ &TTSOpsMinimalTuple);
+
+ dstate->resowner = ResourceOwnerCreate(CurrentResourceOwner,
+ "logical decoding");
+
+ ctx->output_writer_private = dstate;
+ return ctx;
+}
+
+/*
+ * Retrieve tuple from ConcurrentChange structure.
+ *
+ * The input data starts with the structure but it might not be appropriately
+ * aligned.
+ */
+static HeapTuple
+get_changed_tuple(char *change)
+{
+ HeapTupleData tup_data;
+ HeapTuple result;
+ char *src;
+
+ /*
+ * Ensure alignment before accessing the fields. (This is why we can't use
+ * heap_copytuple() instead of this function.)
+ */
+ src = change + offsetof(ConcurrentChange, tup_data);
+ memcpy(&tup_data, src, sizeof(HeapTupleData));
+
+ result = (HeapTuple) palloc(HEAPTUPLESIZE + tup_data.t_len);
+ memcpy(result, &tup_data, sizeof(HeapTupleData));
+ result->t_data = (HeapTupleHeader) ((char *) result + HEAPTUPLESIZE);
+ src = change + SizeOfConcurrentChange;
+ memcpy(result->t_data, src, result->t_len);
+
+ return result;
+}
+
+/*
+ * Decode logical changes from the WAL sequence up to end_of_wal.
+ */
+void
+repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
+ XLogRecPtr end_of_wal)
+{
+ RepackDecodingState *dstate;
+ ResourceOwner resowner_old;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+ resowner_old = CurrentResourceOwner;
+ CurrentResourceOwner = dstate->resowner;
+
+ PG_TRY();
+ {
+ while (ctx->reader->EndRecPtr < end_of_wal)
+ {
+ XLogRecord *record;
+ XLogSegNo segno_new;
+ char *errm = NULL;
+ XLogRecPtr end_lsn;
+
+ record = XLogReadRecord(ctx->reader, &errm);
+ if (errm)
+ elog(ERROR, "%s", errm);
+
+ if (record != NULL)
+ LogicalDecodingProcessRecord(ctx, ctx->reader);
+
+ /*
+ * If WAL segment boundary has been crossed, inform the decoding
+ * system that the catalog_xmin can advance. (We can confirm more
+ * often, but a filling a single WAL segment should not take much
+ * time.)
+ */
+ end_lsn = ctx->reader->EndRecPtr;
+ XLByteToSeg(end_lsn, segno_new, wal_segment_size);
+ if (segno_new != repack_current_segment)
+ {
+ LogicalConfirmReceivedLocation(end_lsn);
+ elog(DEBUG1, "REPACK: confirmed receive location %X/%X",
+ (uint32) (end_lsn >> 32), (uint32) end_lsn);
+ repack_current_segment = segno_new;
+ }
+
+ CHECK_FOR_INTERRUPTS();
+ }
+ InvalidateSystemCaches();
+ CurrentResourceOwner = resowner_old;
+ }
+ PG_CATCH();
+ {
+ /* clear all timetravel entries */
+ InvalidateSystemCaches();
+ CurrentResourceOwner = resowner_old;
+ PG_RE_THROW();
+ }
+ PG_END_TRY();
+}
+
+/*
+ * Apply changes stored in 'file'.
+ */
+static void
+apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
+{
+ Relation rel = dest->rel;
+ TupleTableSlot *index_slot,
+ *ident_slot;
+ HeapTuple tup_old = NULL;
+
+ if (dstate->nchanges == 0)
+ return;
+
+ /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
+ index_slot = MakeSingleTupleTableSlot(dstate->tupdesc, &TTSOpsHeapTuple);
+
+ /* A slot to fetch tuples from identity index. */
+ ident_slot = table_slot_create(rel, NULL);
+
+ while (tuplestore_gettupleslot(dstate->tstore, true, false,
+ dstate->tsslot))
+ {
+ bool shouldFree;
+ HeapTuple tup_change,
+ tup,
+ tup_exist;
+ char *change_raw,
+ *src;
+ ConcurrentChange change;
+ bool isnull[1];
+ Datum values[1];
+
+ CHECK_FOR_INTERRUPTS();
+
+ /* Get the change from the single-column tuple. */
+ tup_change = ExecFetchSlotHeapTuple(dstate->tsslot, false, &shouldFree);
+ heap_deform_tuple(tup_change, dstate->tupdesc_change, values, isnull);
+ Assert(!isnull[0]);
+
+ /* Make sure we access aligned data. */
+ change_raw = (char *) DatumGetByteaP(values[0]);
+ src = (char *) VARDATA(change_raw);
+ memcpy(&change, src, SizeOfConcurrentChange);
+
+ /*
+ * Extract the tuple from the change. The tuple is copied here because
+ * it might be assigned to 'tup_old', in which case it needs to
+ * survive into the next iteration.
+ */
+ tup = get_changed_tuple(src);
+
+ if (change.kind == CHANGE_UPDATE_OLD)
+ {
+ Assert(tup_old == NULL);
+ tup_old = tup;
+ }
+ else if (change.kind == CHANGE_INSERT)
+ {
+ Assert(tup_old == NULL);
+
+ apply_concurrent_insert(rel, tup, dest->iistate, index_slot);
+
+ pfree(tup);
+ }
+ else if (change.kind == CHANGE_UPDATE_NEW ||
+ change.kind == CHANGE_DELETE)
+ {
+ HeapTuple tup_key;
+
+ if (change.kind == CHANGE_UPDATE_NEW)
+ {
+ tup_key = tup_old != NULL ? tup_old : tup;
+ }
+ else
+ {
+ Assert(tup_old == NULL);
+ tup_key = tup;
+ }
+
+ /*
+ * Find the tuple to be updated or deleted.
+ */
+ tup_exist = find_target_tuple(rel, dest, tup_key, ident_slot);
+ if (tup_exist == NULL)
+ elog(ERROR, "failed to find target tuple");
+
+ if (change.kind == CHANGE_UPDATE_NEW)
+ apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
+ index_slot);
+ else
+ apply_concurrent_delete(rel, tup_exist);
+
+ if (tup_old != NULL)
+ {
+ pfree(tup_old);
+ tup_old = NULL;
+ }
+
+ pfree(tup);
+ }
+ else
+ elog(ERROR, "unrecognized kind of change: %d", change.kind);
+
+ /*
+ * If a change was applied now, increment CID for next writes and
+ * update the snapshot so it sees the changes we've applied so far.
+ */
+ if (change.kind != CHANGE_UPDATE_OLD)
+ {
+ CommandCounterIncrement();
+ UpdateActiveSnapshotCommandId();
+ }
+
+ /* TTSOpsMinimalTuple has .get_heap_tuple==NULL. */
+ Assert(shouldFree);
+ pfree(tup_change);
+ }
+
+ tuplestore_clear(dstate->tstore);
+ dstate->nchanges = 0;
+
+ /* Cleanup. */
+ ExecDropSingleTupleTableSlot(index_slot);
+ ExecDropSingleTupleTableSlot(ident_slot);
+}
+
+static void
+apply_concurrent_insert(Relation rel, HeapTuple tup, IndexInsertState *iistate,
+ TupleTableSlot *index_slot)
+{
+ List *recheck;
+
+
+ /*
+ * Like simple_heap_insert(), but make sure that the INSERT is not
+ * logically decoded - see reform_and_rewrite_tuple() for more
+ * information.
+ */
+ heap_insert(rel, tup, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL,
+ NULL);
+
+ /*
+ * Update indexes.
+ *
+ * In case functions in the index need the active snapshot and caller
+ * hasn't set one.
+ */
+ ExecStoreHeapTuple(tup, index_slot, false);
+ recheck = ExecInsertIndexTuples(iistate->rri,
+ index_slot,
+ iistate->estate,
+ false, /* update */
+ false, /* noDupErr */
+ NULL, /* specConflict */
+ NIL, /* arbiterIndexes */
+ false /* onlySummarizing */
+ );
+
+ /*
+ * If recheck is required, it must have been preformed on the source
+ * relation by now. (All the logical changes we process here are already
+ * committed.)
+ */
+ list_free(recheck);
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
+}
+
+static void
+apply_concurrent_update(Relation rel, HeapTuple tup, HeapTuple tup_target,
+ IndexInsertState *iistate, TupleTableSlot *index_slot)
+{
+ LockTupleMode lockmode;
+ TM_FailureData tmfd;
+ TU_UpdateIndexes update_indexes;
+ TM_Result res;
+ List *recheck;
+
+ /*
+ * Write the new tuple into the new heap. ('tup' gets the TID assigned
+ * here.)
+ *
+ * Do it like in simple_heap_update(), except for 'wal_logical' (and
+ * except for 'wait').
+ */
+ res = heap_update(rel, &tup_target->t_self, tup,
+ GetCurrentCommandId(true),
+ InvalidSnapshot,
+ false, /* no wait - only we are doing changes */
+ &tmfd, &lockmode, &update_indexes,
+ false /* wal_logical */ );
+ if (res != TM_Ok)
+ ereport(ERROR, (errmsg("failed to apply concurrent UPDATE")));
+
+ ExecStoreHeapTuple(tup, index_slot, false);
+
+ if (update_indexes != TU_None)
+ {
+ recheck = ExecInsertIndexTuples(iistate->rri,
+ index_slot,
+ iistate->estate,
+ true, /* update */
+ false, /* noDupErr */
+ NULL, /* specConflict */
+ NIL, /* arbiterIndexes */
+ /* onlySummarizing */
+ update_indexes == TU_Summarizing);
+ list_free(recheck);
+ }
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
+}
+
+static void
+apply_concurrent_delete(Relation rel, HeapTuple tup_target)
+{
+ TM_Result res;
+ TM_FailureData tmfd;
+
+ /*
+ * Delete tuple from the new heap.
+ *
+ * Do it like in simple_heap_delete(), except for 'wal_logical' (and
+ * except for 'wait').
+ */
+ res = heap_delete(rel, &tup_target->t_self, GetCurrentCommandId(true),
+ InvalidSnapshot, false,
+ &tmfd,
+ false, /* no wait - only we are doing changes */
+ false /* wal_logical */ );
+
+ if (res != TM_Ok)
+ ereport(ERROR, (errmsg("failed to apply concurrent DELETE")));
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1);
+}
+
+/*
+ * Find the tuple to be updated or deleted.
+ *
+ * 'tup_key' is a tuple containing the key values for the scan.
+ *
+ * On exit,'*scan_p' contains the scan descriptor used. The caller must close
+ * it when he no longer needs the tuple returned.
+ */
+static HeapTuple
+find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
+ TupleTableSlot *ident_slot)
+{
+ Relation ident_index = dest->ident_index;
+ IndexScanDesc scan;
+ Form_pg_index ident_form;
+ int2vector *ident_indkey;
+ HeapTuple result = NULL;
+
+ /* XXX no instrumentation for now */
+ scan = index_beginscan(rel, ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0);
+
+ /*
+ * Scan key is passed by caller, so it does not have to be constructed
+ * multiple times. Key entries have all fields initialized, except for
+ * sk_argument.
+ */
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
+
+ /* Info needed to retrieve key values from heap tuple. */
+ ident_form = ident_index->rd_index;
+ ident_indkey = &ident_form->indkey;
+
+ /* Use the incoming tuple to finalize the scan key. */
+ for (int i = 0; i < scan->numberOfKeys; i++)
+ {
+ ScanKey entry;
+ bool isnull;
+ int16 attno_heap;
+
+ entry = &scan->keyData[i];
+ attno_heap = ident_indkey->values[i];
+ entry->sk_argument = heap_getattr(tup_key,
+ attno_heap,
+ rel->rd_att,
+ &isnull);
+ Assert(!isnull);
+ }
+ if (index_getnext_slot(scan, ForwardScanDirection, ident_slot))
+ {
+ bool shouldFree;
+
+ result = ExecFetchSlotHeapTuple(ident_slot, false, &shouldFree);
+ /* TTSOpsBufferHeapTuple has .get_heap_tuple != NULL. */
+ Assert(!shouldFree);
+ }
+ index_endscan(scan);
+
+ return result;
+}
+
+/*
+ * Decode and apply concurrent changes.
+ */
+static void
+process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
+ XLogRecPtr end_of_wal, ChangeDest *dest)
+{
+ RepackDecodingState *dstate;
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_CATCH_UP);
+
+ dstate = (RepackDecodingState *) decoding_ctx->output_writer_private;
+
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+
+ if (dstate->nchanges == 0)
+ return;
+
+ apply_concurrent_changes(dstate, dest);
+}
+
+/*
+ * Initialize IndexInsertState for index specified by ident_index_id.
+ *
+ * While doing that, also return the identity index in *ident_index_p.
+ */
+static IndexInsertState *
+get_index_insert_state(Relation relation, Oid ident_index_id,
+ Relation *ident_index_p)
+{
+ EState *estate;
+ int i;
+ IndexInsertState *result;
+ Relation ident_index = NULL;
+
+ result = (IndexInsertState *) palloc0(sizeof(IndexInsertState));
+ estate = CreateExecutorState();
+
+ result->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(result->rri, relation, 0, 0, 0);
+ ExecOpenIndices(result->rri, false);
+
+ /*
+ * Find the relcache entry of the identity index so that we spend no extra
+ * effort to open / close it.
+ */
+ for (i = 0; i < result->rri->ri_NumIndices; i++)
+ {
+ Relation ind_rel;
+
+ ind_rel = result->rri->ri_IndexRelationDescs[i];
+ if (ind_rel->rd_id == ident_index_id)
+ ident_index = ind_rel;
+ }
+ if (ident_index == NULL)
+ elog(ERROR, "failed to open identity index");
+
+ /* Only initialize fields needed by ExecInsertIndexTuples(). */
+ result->estate = estate;
+
+ *ident_index_p = ident_index;
+ return result;
+}
+
+/*
+ * Build scan key to process logical changes.
+ */
+static ScanKey
+build_identity_key(Oid ident_idx_oid, Relation rel_src, int *nentries)
+{
+ Relation ident_idx_rel;
+ Form_pg_index ident_idx;
+ int n,
+ i;
+ ScanKey result;
+
+ Assert(OidIsValid(ident_idx_oid));
+ ident_idx_rel = index_open(ident_idx_oid, AccessShareLock);
+ ident_idx = ident_idx_rel->rd_index;
+ n = ident_idx->indnatts;
+ result = (ScanKey) palloc(sizeof(ScanKeyData) * n);
+ for (i = 0; i < n; i++)
+ {
+ ScanKey entry;
+ int16 relattno;
+ Form_pg_attribute att;
+ Oid opfamily,
+ opcintype,
+ opno,
+ opcode;
+
+ entry = &result[i];
+ relattno = ident_idx->indkey.values[i];
+ if (relattno >= 1)
+ {
+ TupleDesc desc;
+
+ desc = rel_src->rd_att;
+ att = TupleDescAttr(desc, relattno - 1);
+ }
+ else
+ elog(ERROR, "unexpected attribute number %d in index", relattno);
+
+ opfamily = ident_idx_rel->rd_opfamily[i];
+ opcintype = ident_idx_rel->rd_opcintype[i];
+ opno = get_opfamily_member(opfamily, opcintype, opcintype,
+ BTEqualStrategyNumber);
+
+ if (!OidIsValid(opno))
+ elog(ERROR, "failed to find = operator for type %u", opcintype);
+
+ opcode = get_opcode(opno);
+ if (!OidIsValid(opcode))
+ elog(ERROR, "failed to find = operator for operator %u", opno);
+
+ /* Initialize everything but argument. */
+ ScanKeyInit(entry,
+ i + 1,
+ BTEqualStrategyNumber, opcode,
+ (Datum) NULL);
+ entry->sk_collation = att->attcollation;
+ }
+ index_close(ident_idx_rel, AccessShareLock);
+
+ *nentries = n;
+ return result;
+}
+
+static void
+free_index_insert_state(IndexInsertState *iistate)
+{
+ ExecCloseIndices(iistate->rri);
+ FreeExecutorState(iistate->estate);
+ pfree(iistate->rri);
+ pfree(iistate);
+}
+
+static void
+cleanup_logical_decoding(LogicalDecodingContext *ctx)
+{
+ RepackDecodingState *dstate;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ ExecDropSingleTupleTableSlot(dstate->tsslot);
+ FreeTupleDesc(dstate->tupdesc_change);
+ FreeTupleDesc(dstate->tupdesc);
+ tuplestore_end(dstate->tstore);
+
+ FreeDecodingContext(ctx);
+
+ ReplicationSlotRelease();
+ ReplicationSlotDrop(NameStr(dstate->slotname), false);
+ pfree(dstate);
+}
+
+/*
+ * The final steps of rebuild_relation() for concurrent processing.
+ *
+ * On entry, NewHeap is locked in AccessExclusiveLock mode. OldHeap and its
+ * clustering index (if one is passed) are still locked in a mode that allows
+ * concurrent data changes. On exit, both tables and their indexes are closed,
+ * but locked in AccessExclusiveLock mode.
+ */
+static void
+rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
+ Relation cl_index,
+ LogicalDecodingContext *decoding_ctx,
+ TransactionId frozenXid,
+ MultiXactId cutoffMulti)
+{
+ LOCKMODE lockmode_old PG_USED_FOR_ASSERTS_ONLY;
+ List *ind_oids_new;
+ Oid old_table_oid = RelationGetRelid(OldHeap);
+ Oid new_table_oid = RelationGetRelid(NewHeap);
+ List *ind_oids_old = RelationGetIndexList(OldHeap);
+ ListCell *lc,
+ *lc2;
+ char relpersistence;
+ bool is_system_catalog;
+ Oid ident_idx_old,
+ ident_idx_new;
+ XLogRecPtr wal_insert_ptr,
+ end_of_wal;
+ char dummy_rec_data = '\0';
+ Relation *ind_refs,
+ *ind_refs_p;
+ int nind;
+ ChangeDest chgdst;
+
+ /* Like in cluster_rel(). */
+ lockmode_old = ShareUpdateExclusiveLock;
+ Assert(CheckRelationLockedByMe(OldHeap, lockmode_old, false));
+ Assert(cl_index == NULL ||
+ CheckRelationLockedByMe(cl_index, lockmode_old, false));
+ /* This is expected from the caller. */
+ Assert(CheckRelationLockedByMe(NewHeap, AccessExclusiveLock, false));
+
+ ident_idx_old = RelationGetReplicaIndex(OldHeap);
+
+ /*
+ * Unlike the exclusive case, we build new indexes for the new relation
+ * rather than swapping the storage and reindexing the old relation. The
+ * point is that the index build can take some time, so we do it before we
+ * get AccessExclusiveLock on the old heap and therefore we cannot swap
+ * the heap storage yet.
+ *
+ * index_create() will lock the new indexes using AccessExclusiveLock - no
+ * need to change that. At the same time, we use ShareUpdateExclusiveLock
+ * to lock the existing indexes - that should be enough to prevent others
+ * from changing them while we're repacking the relation. The lock on
+ * table should prevent others from changing the index column list, but
+ * might not be enough for commands like ALTER INDEX ... SET ... (Those
+ * are not necessarily dangerous, but can make user confused if the
+ * changes they do get lost due to REPACK.)
+ */
+ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
+
+ /*
+ * Processing shouldn't start w/o valid identity index.
+ */
+ Assert(OidIsValid(ident_idx_old));
+
+ /* Find "identity index" on the new relation. */
+ ident_idx_new = InvalidOid;
+ forboth(lc, ind_oids_old, lc2, ind_oids_new)
+ {
+ Oid ind_old = lfirst_oid(lc);
+ Oid ind_new = lfirst_oid(lc2);
+
+ if (ident_idx_old == ind_old)
+ {
+ ident_idx_new = ind_new;
+ break;
+ }
+ }
+ if (!OidIsValid(ident_idx_new))
+
+ /*
+ * Should not happen, given our lock on the old relation.
+ */
+ ereport(ERROR,
+ (errmsg("identity index missing on the new relation")));
+
+ /* Gather information to apply concurrent changes. */
+ chgdst.rel = NewHeap;
+ chgdst.iistate = get_index_insert_state(NewHeap, ident_idx_new,
+ &chgdst.ident_index);
+ chgdst.ident_key = build_identity_key(ident_idx_new, OldHeap,
+ &chgdst.ident_key_nentries);
+
+ /*
+ * During testing, wait for another backend to perform concurrent data
+ * changes which we will process below.
+ */
+ INJECTION_POINT("repack-concurrently-before-lock", NULL);
+
+ /*
+ * Flush all WAL records inserted so far (possibly except for the last
+ * incomplete page, see GetInsertRecPtr), to minimize the amount of data
+ * we need to flush while holding exclusive lock on the source table.
+ */
+ wal_insert_ptr = GetInsertRecPtr();
+ XLogFlush(wal_insert_ptr);
+ end_of_wal = GetFlushRecPtr(NULL);
+
+ /*
+ * Apply concurrent changes first time, to minimize the time we need to
+ * hold AccessExclusiveLock. (Quite some amount of WAL could have been
+ * written during the data copying and index creation.)
+ */
+ process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+
+ /*
+ * Acquire AccessExclusiveLock on the table, its TOAST relation (if there
+ * is one), all its indexes, so that we can swap the files.
+ *
+ * Before that, unlock the index temporarily to avoid deadlock in case
+ * another transaction is trying to lock it while holding the lock on the
+ * table.
+ */
+ if (cl_index)
+ {
+ index_close(cl_index, ShareUpdateExclusiveLock);
+ cl_index = NULL;
+ }
+ /* For the same reason, unlock TOAST relation. */
+ if (OldHeap->rd_rel->reltoastrelid)
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+ /* Finally lock the table */
+ LockRelationOid(old_table_oid, AccessExclusiveLock);
+
+ /*
+ * Lock all indexes now, not only the clustering one: all indexes need to
+ * have their files swapped. While doing that, store their relation
+ * references in an array, to handle predicate locks below.
+ */
+ ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
+ nind = 0;
+ foreach(lc, ind_oids_old)
+ {
+ Oid ind_oid;
+ Relation index;
+
+ ind_oid = lfirst_oid(lc);
+ index = index_open(ind_oid, AccessExclusiveLock);
+
+ /*
+ * TODO 1) Do we need to check if ALTER INDEX was executed since the
+ * new index was created in build_new_indexes()? 2) Specifically for
+ * the clustering index, should check_index_is_clusterable() be called
+ * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
+ * table probably blocks all commands that affect the result of
+ * check_index_is_clusterable().)
+ */
+ *ind_refs_p = index;
+ ind_refs_p++;
+ nind++;
+ }
+
+ /*
+ * In addition, lock the OldHeap's TOAST relation exclusively - again, the
+ * lock is needed to swap the files.
+ */
+ if (OidIsValid(OldHeap->rd_rel->reltoastrelid))
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+
+ /*
+ * Tuples and pages of the old heap will be gone, but the heap will stay.
+ */
+ TransferPredicateLocksToHeapRelation(OldHeap);
+ /* The same for indexes. */
+ for (int i = 0; i < nind; i++)
+ {
+ Relation index = ind_refs[i];
+
+ TransferPredicateLocksToHeapRelation(index);
+
+ /*
+ * References to indexes on the old relation are not needed anymore,
+ * however locks stay till the end of the transaction.
+ */
+ index_close(index, NoLock);
+ }
+ pfree(ind_refs);
+
+ /*
+ * Flush anything we see in WAL, to make sure that all changes committed
+ * while we were waiting for the exclusive lock are available for
+ * decoding. This should not be necessary if all backends had
+ * synchronous_commit set, but we can't rely on this setting.
+ *
+ * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
+ * position, and GetLastImportantRecPtr() points at the start of the last
+ * record rather than at the end. Thus the simplest way to determine the
+ * insert position is to insert a dummy record and use its LSN.
+ *
+ * XXX Consider using GetLastImportantRecPtr() and adding the size of the
+ * last record (plus the total size of all the page headers the record
+ * spans)?
+ */
+ XLogBeginInsert();
+ XLogRegisterData(&dummy_rec_data, 1);
+ wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
+ XLogFlush(wal_insert_ptr);
+ end_of_wal = GetFlushRecPtr(NULL);
+
+ /* Apply the concurrent changes again. */
+ process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+
+ /* Remember info about rel before closing OldHeap */
+ relpersistence = OldHeap->rd_rel->relpersistence;
+ is_system_catalog = IsSystemRelation(OldHeap);
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_SWAP_REL_FILES);
+
+ /*
+ * Even ShareUpdateExclusiveLock should have prevented others from
+ * creating / dropping indexes (even using the CONCURRENTLY option), so we
+ * do not need to check whether the lists match.
+ */
+ forboth(lc, ind_oids_old, lc2, ind_oids_new)
+ {
+ Oid ind_old = lfirst_oid(lc);
+ Oid ind_new = lfirst_oid(lc2);
+ Oid mapped_tables[4];
+
+ /* Zero out possible results from swapped_relation_files */
+ memset(mapped_tables, 0, sizeof(mapped_tables));
+
+ swap_relation_files(ind_old, ind_new,
+ (old_table_oid == RelationRelationId),
+ false, /* swap_toast_by_content */
+ true,
+ InvalidTransactionId,
+ InvalidMultiXactId,
+ mapped_tables);
+
+#ifdef USE_ASSERT_CHECKING
+
+ /*
+ * Concurrent processing is not supported for system relations, so
+ * there should be no mapped tables.
+ */
+ for (int i = 0; i < 4; i++)
+ Assert(mapped_tables[i] == 0);
+#endif
+ }
+
+ /* The new indexes must be visible for deletion. */
+ CommandCounterIncrement();
+
+ /* Close the old heap but keep lock until transaction commit. */
+ table_close(OldHeap, NoLock);
+ /* Close the new heap. (We didn't have to open its indexes). */
+ table_close(NewHeap, NoLock);
+
+ /* Cleanup what we don't need anymore. (And close the identity index.) */
+ pfree(chgdst.ident_key);
+ free_index_insert_state(chgdst.iistate);
+
+ /*
+ * Swap the relations and their TOAST relations and TOAST indexes. This
+ * also drops the new relation and its indexes.
+ *
+ * (System catalogs are currently not supported.)
+ */
+ Assert(!is_system_catalog);
+ finish_heap_swap(old_table_oid, new_table_oid,
+ is_system_catalog,
+ false, /* swap_toast_by_content */
+ false, true, false,
+ frozenXid, cutoffMulti,
+ relpersistence);
+}
+
+/*
+ * Build indexes on NewHeap according to those on OldHeap.
+ *
+ * OldIndexes is the list of index OIDs on OldHeap. The contained indexes end
+ * up locked using ShareUpdateExclusiveLock.
+ *
+ * A list of OIDs of the corresponding indexes created on NewHeap is
+ * returned. The order of items does match, so we can use these arrays to swap
+ * index storage.
+ */
+static List *
+build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
+{
+ ListCell *lc;
+ List *result = NIL;
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_REBUILD_INDEX);
+
+ foreach(lc, OldIndexes)
+ {
+ Oid ind_oid,
+ ind_oid_new;
+ char *newName;
+ Relation ind;
+
+ ind_oid = lfirst_oid(lc);
+ ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+
+ newName = ChooseRelationName(get_rel_name(ind_oid),
+ NULL,
+ "repacknew",
+ get_rel_namespace(ind->rd_index->indrelid),
+ false);
+ ind_oid_new = index_create_copy(NewHeap, ind_oid,
+ ind->rd_rel->reltablespace, newName,
+ false);
+ result = lappend_oid(result, ind_oid_new);
+
+ index_close(ind, NoLock);
+ }
+
+ return result;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index a1fd4cab35b..85d289ca22b 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -892,7 +892,7 @@ refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
static void
refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersistence)
{
- finish_heap_swap(matviewOid, OIDNewHeap, false, false, true, true,
+ finish_heap_swap(matviewOid, OIDNewHeap, false, false, true, true, true,
RecentXmin, ReadNextMultiXactId(), relpersistence);
}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 1c9ef53be20..d3235df6c11 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -5992,6 +5992,7 @@ ATRewriteTables(AlterTableStmt *parsetree, List **wqueue, LOCKMODE lockmode,
finish_heap_swap(tab->relid, OIDNewHeap,
false, false, true,
!OidIsValid(tab->newTableSpace),
+ true,
RecentXmin,
ReadNextMultiXactId(),
persistence);
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index 6afa203983f..ae8b5d4066f 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -126,7 +126,7 @@ static void vac_truncate_clog(TransactionId frozenXID,
TransactionId lastSaneFrozenXid,
MultiXactId lastSaneMinMulti);
static bool vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
- BufferAccessStrategy bstrategy);
+ BufferAccessStrategy bstrategy, bool isTopLevel);
static double compute_parallel_delay(void);
static VacOptValue get_vacoptval_from_boolean(DefElem *def);
static bool vac_tid_reaped(ItemPointer itemptr, void *state);
@@ -629,7 +629,8 @@ vacuum(List *relations, const VacuumParams params, BufferAccessStrategy bstrateg
if (params.options & VACOPT_VACUUM)
{
- if (!vacuum_rel(vrel->oid, vrel->relation, params, bstrategy))
+ if (!vacuum_rel(vrel->oid, vrel->relation, params, bstrategy,
+ isTopLevel))
continue;
}
@@ -1999,7 +2000,7 @@ vac_truncate_clog(TransactionId frozenXID,
*/
static bool
vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
- BufferAccessStrategy bstrategy)
+ BufferAccessStrategy bstrategy, bool isTopLevel)
{
LOCKMODE lmode;
Relation rel;
@@ -2290,7 +2291,7 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
/* VACUUM FULL is a variant of REPACK; see cluster.c */
cluster_rel(REPACK_COMMAND_VACUUMFULL, rel, InvalidOid,
- &cluster_params);
+ &cluster_params, isTopLevel);
/* cluster_rel closes the relation, but keeps lock */
rel = NULL;
@@ -2333,7 +2334,8 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
toast_vacuum_params.options |= VACOPT_PROCESS_MAIN;
toast_vacuum_params.toast_parent = relid;
- vacuum_rel(toast_relid, NULL, toast_vacuum_params, bstrategy);
+ vacuum_rel(toast_relid, NULL, toast_vacuum_params, bstrategy,
+ isTopLevel);
}
/*
diff --git a/src/backend/meson.build b/src/backend/meson.build
index b831a541652..5c148131217 100644
--- a/src/backend/meson.build
+++ b/src/backend/meson.build
@@ -194,5 +194,6 @@ pg_test_mod_args = pg_mod_args + {
subdir('jit/llvm')
subdir('replication/libpqwalreceiver')
subdir('replication/pgoutput')
+subdir('replication/pgoutput_repack')
subdir('snowball')
subdir('utils/mb/conversion_procs')
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index cc03f0706e9..a956892f42f 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -33,6 +33,7 @@
#include "access/xlogreader.h"
#include "access/xlogrecord.h"
#include "catalog/pg_control.h"
+#include "commands/cluster.h"
#include "replication/decode.h"
#include "replication/logical.h"
#include "replication/message.h"
@@ -472,6 +473,88 @@ heap_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
TransactionId xid = XLogRecGetXid(buf->record);
SnapBuild *builder = ctx->snapshot_builder;
+ /*
+ * If the change is not intended for logical decoding, do not even
+ * establish transaction for it - REPACK CONCURRENTLY is the typical use
+ * case.
+ *
+ * First, check if REPACK CONCURRENTLY is being performed by this backend.
+ * If so, only decode data changes of the table that it is processing, and
+ * the changes of its TOAST relation.
+ *
+ * (TOAST locator should not be set unless the main is.)
+ */
+ Assert(!OidIsValid(repacked_rel_toast_locator.relNumber) ||
+ OidIsValid(repacked_rel_locator.relNumber));
+
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ {
+ XLogReaderState *r = buf->record;
+ RelFileLocator locator;
+
+ /* Not all records contain the block. */
+ if (XLogRecGetBlockTagExtended(r, 0, &locator, NULL, NULL, NULL) &&
+ !RelFileLocatorEquals(locator, repacked_rel_locator) &&
+ (!OidIsValid(repacked_rel_toast_locator.relNumber) ||
+ !RelFileLocatorEquals(locator, repacked_rel_toast_locator)))
+ return;
+ }
+
+ /*
+ * Second, skip records which do not contain sufficient information for
+ * the decoding.
+ *
+ * The problem we solve here is that REPACK CONCURRENTLY generates WAL
+ * when doing changes in the new table. Those changes should not be useful
+ * for any other user (such as logical replication subscription) because
+ * the new table will eventually be dropped (after REPACK CONCURRENTLY has
+ * assigned its file to the "old table").
+ */
+ switch (info)
+ {
+ case XLOG_HEAP_INSERT:
+ {
+ xl_heap_insert *rec;
+
+ rec = (xl_heap_insert *) XLogRecGetData(buf->record);
+
+ /*
+ * This does happen when 1) raw_heap_insert marks the TOAST
+ * record as HEAP_INSERT_NO_LOGICAL, 2) REPACK CONCURRENTLY
+ * replays inserts performed by other backends.
+ */
+ if ((rec->flags & XLH_INSERT_CONTAINS_NEW_TUPLE) == 0)
+ return;
+
+ break;
+ }
+
+ case XLOG_HEAP_HOT_UPDATE:
+ case XLOG_HEAP_UPDATE:
+ {
+ xl_heap_update *rec;
+
+ rec = (xl_heap_update *) XLogRecGetData(buf->record);
+ if ((rec->flags &
+ (XLH_UPDATE_CONTAINS_NEW_TUPLE |
+ XLH_UPDATE_CONTAINS_OLD_TUPLE |
+ XLH_UPDATE_CONTAINS_OLD_KEY)) == 0)
+ return;
+
+ break;
+ }
+
+ case XLOG_HEAP_DELETE:
+ {
+ xl_heap_delete *rec;
+
+ rec = (xl_heap_delete *) XLogRecGetData(buf->record);
+ if (rec->flags & XLH_DELETE_NO_LOGICAL)
+ return;
+ break;
+ }
+ }
+
ReorderBufferProcessXid(ctx->reorder, xid, buf->origptr);
/*
@@ -512,6 +595,17 @@ heap_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
break;
case XLOG_HEAP_TRUNCATE:
+ /* Is REPACK (CONCURRENTLY) being run by this backend? */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+
+ /*
+ * TRUNCATE changes rd_locator of the relation, so it'd break
+ * REPACK (CONCURRENTLY). In fact it should not happen because
+ * TRUNCATE needs AccessExclusiveLock on the table. Should we
+ * only use Assert() here?
+ */
+ ereport(ERROR,
+ (errmsg("TRUNCATE encountered while doing REPACK (CONCURRENTLY)")));
if (SnapBuildProcessChange(builder, xid, buf->origptr) &&
!ctx->fast_forward)
DecodeTruncate(ctx, buf);
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index a3730804428..7643dfe31bb 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -486,6 +486,27 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
return SnapBuildMVCCFromHistoric(snap, true);
}
+/*
+ * Build an MVCC snapshot for the initial data load performed by REPACK
+ * CONCURRENTLY command.
+ *
+ * The snapshot will only be used to scan one particular relation, which is
+ * treated like a catalog (therefore ->building_full_snapshot is not
+ * important), and the caller should already have a replication slot setup (so
+ * we do not set MyProc->xmin). XXX Do we yet need to add some restrictions?
+ */
+Snapshot
+SnapBuildInitialSnapshotForRepack(SnapBuild *builder)
+{
+ Snapshot snap;
+
+ Assert(builder->state == SNAPBUILD_CONSISTENT);
+ Assert(builder->building_full_snapshot);
+
+ snap = SnapBuildBuildSnapshot(builder);
+ return SnapBuildMVCCFromHistoric(snap, false);
+}
+
/*
* Turn a historic MVCC snapshot into an ordinary MVCC snapshot.
*
diff --git a/src/backend/replication/pgoutput_repack/Makefile b/src/backend/replication/pgoutput_repack/Makefile
new file mode 100644
index 00000000000..4efeb713b70
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/Makefile
@@ -0,0 +1,32 @@
+#-------------------------------------------------------------------------
+#
+# Makefile--
+# Makefile for src/backend/replication/pgoutput_repack
+#
+# IDENTIFICATION
+# src/backend/replication/pgoutput_repack
+#
+#-------------------------------------------------------------------------
+
+subdir = src/backend/replication/pgoutput_repack
+top_builddir = ../../../..
+include $(top_builddir)/src/Makefile.global
+
+OBJS = \
+ $(WIN32RES) \
+ pgoutput_repack.o
+PGFILEDESC = "pgoutput_repack - logical replication output plugin for REPACK command"
+NAME = pgoutput_repack
+
+all: all-shared-lib
+
+include $(top_srcdir)/src/Makefile.shlib
+
+install: all installdirs install-lib
+
+installdirs: installdirs-lib
+
+uninstall: uninstall-lib
+
+clean distclean: clean-lib
+ rm -f $(OBJS)
diff --git a/src/backend/replication/pgoutput_repack/meson.build b/src/backend/replication/pgoutput_repack/meson.build
new file mode 100644
index 00000000000..133e865a4a0
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/meson.build
@@ -0,0 +1,18 @@
+# Copyright (c) 2022-2024, PostgreSQL Global Development Group
+
+pgoutput_repack_sources = files(
+ 'pgoutput_repack.c',
+)
+
+if host_system == 'windows'
+ pgoutput_repack_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+ '--NAME', 'pgoutput_repack',
+ '--FILEDESC', 'pgoutput_repack - logical replication output plugin for REPACK command',])
+endif
+
+pgoutput_repack = shared_module('pgoutput_repack',
+ pgoutput_repack_sources,
+ kwargs: pg_mod_args,
+)
+
+backend_targets += pgoutput_repack
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
new file mode 100644
index 00000000000..c8930640a0d
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -0,0 +1,240 @@
+/*-------------------------------------------------------------------------
+ *
+ * pgoutput_repack.c
+ * Logical Replication output plugin for REPACK command
+ *
+ * Copyright (c) 2012-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * src/backend/replication/pgoutput_repack/pgoutput_repack.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/heaptoast.h"
+#include "commands/cluster.h"
+#include "replication/snapbuild.h"
+#include "utils/memutils.h"
+
+PG_MODULE_MAGIC;
+
+static void plugin_startup(LogicalDecodingContext *ctx,
+ OutputPluginOptions *opt, bool is_init);
+static void plugin_shutdown(LogicalDecodingContext *ctx);
+static void plugin_begin_txn(LogicalDecodingContext *ctx,
+ ReorderBufferTXN *txn);
+static void plugin_commit_txn(LogicalDecodingContext *ctx,
+ ReorderBufferTXN *txn, XLogRecPtr commit_lsn);
+static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ Relation rel, ReorderBufferChange *change);
+static void store_change(LogicalDecodingContext *ctx,
+ ConcurrentChangeKind kind, HeapTuple tuple);
+
+void
+_PG_output_plugin_init(OutputPluginCallbacks *cb)
+{
+ AssertVariableIsOfType(&_PG_output_plugin_init, LogicalOutputPluginInit);
+
+ cb->startup_cb = plugin_startup;
+ cb->begin_cb = plugin_begin_txn;
+ cb->change_cb = plugin_change;
+ cb->commit_cb = plugin_commit_txn;
+ cb->shutdown_cb = plugin_shutdown;
+}
+
+
+/* initialize this plugin */
+static void
+plugin_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt,
+ bool is_init)
+{
+ ctx->output_plugin_private = NULL;
+
+ /* Probably unnecessary, as we don't use the SQL interface ... */
+ opt->output_type = OUTPUT_PLUGIN_BINARY_OUTPUT;
+
+ if (ctx->output_plugin_options != NIL)
+ {
+ ereport(ERROR,
+ (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("This plugin does not expect any options")));
+ }
+}
+
+static void
+plugin_shutdown(LogicalDecodingContext *ctx)
+{
+}
+
+/*
+ * As we don't release the slot during processing of particular table, there's
+ * no room for SQL interface, even for debugging purposes. Therefore we need
+ * neither OutputPluginPrepareWrite() nor OutputPluginWrite() in the plugin
+ * callbacks. (Although we might want to write custom callbacks, this API
+ * seems to be unnecessarily generic for our purposes.)
+ */
+
+/* BEGIN callback */
+static void
+plugin_begin_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn)
+{
+}
+
+/* COMMIT callback */
+static void
+plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ XLogRecPtr commit_lsn)
+{
+}
+
+/*
+ * Callback for individual changed tuples
+ */
+static void
+plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ Relation relation, ReorderBufferChange *change)
+{
+ RepackDecodingState *dstate;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ /* Only interested in one particular relation. */
+ if (relation->rd_id != dstate->relid)
+ return;
+
+ /* Decode entry depending on its type */
+ switch (change->action)
+ {
+ case REORDER_BUFFER_CHANGE_INSERT:
+ {
+ HeapTuple newtuple;
+
+ newtuple = change->data.tp.newtuple != NULL ?
+ change->data.tp.newtuple : NULL;
+
+ /*
+ * Identity checks in the main function should have made this
+ * impossible.
+ */
+ if (newtuple == NULL)
+ elog(ERROR, "Incomplete insert info.");
+
+ store_change(ctx, CHANGE_INSERT, newtuple);
+ }
+ break;
+ case REORDER_BUFFER_CHANGE_UPDATE:
+ {
+ HeapTuple oldtuple,
+ newtuple;
+
+ oldtuple = change->data.tp.oldtuple != NULL ?
+ change->data.tp.oldtuple : NULL;
+ newtuple = change->data.tp.newtuple != NULL ?
+ change->data.tp.newtuple : NULL;
+
+ if (newtuple == NULL)
+ elog(ERROR, "Incomplete update info.");
+
+ if (oldtuple != NULL)
+ store_change(ctx, CHANGE_UPDATE_OLD, oldtuple);
+
+ store_change(ctx, CHANGE_UPDATE_NEW, newtuple);
+ }
+ break;
+ case REORDER_BUFFER_CHANGE_DELETE:
+ {
+ HeapTuple oldtuple;
+
+ oldtuple = change->data.tp.oldtuple ?
+ change->data.tp.oldtuple : NULL;
+
+ if (oldtuple == NULL)
+ elog(ERROR, "Incomplete delete info.");
+
+ store_change(ctx, CHANGE_DELETE, oldtuple);
+ }
+ break;
+ default:
+ /* Should not come here */
+ Assert(false);
+ break;
+ }
+}
+
+/* Store concurrent data change. */
+static void
+store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
+ HeapTuple tuple)
+{
+ RepackDecodingState *dstate;
+ char *change_raw;
+ ConcurrentChange change;
+ bool flattened = false;
+ Size size;
+ Datum values[1];
+ bool isnull[1];
+ char *dst;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ size = VARHDRSZ + SizeOfConcurrentChange;
+
+ /*
+ * ReorderBufferCommit() stores the TOAST chunks in its private memory
+ * context and frees them after having called apply_change(). Therefore
+ * we need flat copy (including TOAST) that we eventually copy into the
+ * memory context which is available to decode_concurrent_changes().
+ */
+ if (HeapTupleHasExternal(tuple))
+ {
+ /*
+ * toast_flatten_tuple_to_datum() might be more convenient but we
+ * don't want the decompression it does.
+ */
+ tuple = toast_flatten_tuple(tuple, dstate->tupdesc);
+ flattened = true;
+ }
+
+ size += tuple->t_len;
+ if (size >= MaxAllocSize)
+ elog(ERROR, "Change is too big.");
+
+ /* Construct the change. */
+ change_raw = (char *) palloc0(size);
+ SET_VARSIZE(change_raw, size);
+
+ /*
+ * Since the varlena alignment might not be sufficient for the structure,
+ * set the fields in a local instance and remember where it should
+ * eventually be copied.
+ */
+ change.kind = kind;
+ dst = (char *) VARDATA(change_raw);
+
+ /*
+ * Copy the tuple.
+ *
+ * Note: change->tup_data.t_data must be fixed on retrieval!
+ */
+ memcpy(&change.tup_data, tuple, sizeof(HeapTupleData));
+ memcpy(dst, &change, SizeOfConcurrentChange);
+ dst += SizeOfConcurrentChange;
+ memcpy(dst, tuple->t_data, tuple->t_len);
+
+ /* The data has been copied. */
+ if (flattened)
+ pfree(tuple);
+
+ /* Store as tuple of 1 bytea column. */
+ values[0] = PointerGetDatum(change_raw);
+ isnull[0] = false;
+ tuplestore_putvalues(dstate->tstore, dstate->tupdesc_change,
+ values, isnull);
+
+ /* Accounting. */
+ dstate->nchanges++;
+
+ /* Cleanup. */
+ pfree(change_raw);
+}
diff --git a/src/backend/storage/lmgr/generate-lwlocknames.pl b/src/backend/storage/lmgr/generate-lwlocknames.pl
index cd3e43c448a..519f3953638 100644
--- a/src/backend/storage/lmgr/generate-lwlocknames.pl
+++ b/src/backend/storage/lmgr/generate-lwlocknames.pl
@@ -162,7 +162,7 @@ while (<$lwlocklist>)
die
"$wait_event_lwlocks[$lwlock_count] defined in wait_event_names.txt but "
- . " missing from lwlocklist.h"
+ . "missing from lwlocklist.h"
if $lwlock_count < scalar @wait_event_lwlocks;
die
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index 4cf32ffe833..93fc3037110 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -214,7 +214,6 @@ static List *exportedSnapshots = NIL;
/* Prototypes for local functions */
static void UnregisterSnapshotNoOwner(Snapshot snapshot);
-static void FreeSnapshot(Snapshot snapshot);
static void SnapshotResetXmin(void);
/* ResourceOwner callbacks to track snapshot references */
@@ -659,7 +658,7 @@ CopySnapshot(Snapshot snapshot)
* FreeSnapshot
* Free the memory associated with a snapshot.
*/
-static void
+void
FreeSnapshot(Snapshot snapshot)
{
Assert(snapshot->regd_count == 0);
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 626d9f1c98b..0fcf343d3af 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -5075,8 +5075,8 @@ match_previous_words(int pattern_id,
* one word, so the above test is correct.
*/
if (ends_with(prev_wd, '(') || ends_with(prev_wd, ','))
- COMPLETE_WITH("ANALYZE", "VERBOSE");
- else if (TailMatches("ANALYZE", "VERBOSE"))
+ COMPLETE_WITH("ANALYZE", "CONCURRENTLY", "VERBOSE");
+ else if (TailMatches("ANALYZE", "CONCURRENTLY", "VERBOSE"))
COMPLETE_WITH("ON", "OFF");
}
diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 632c4332a8c..b7cd25896f6 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -361,14 +361,15 @@ extern void heap_multi_insert(Relation relation, TupleTableSlot **slots,
BulkInsertState bistate);
extern TM_Result heap_delete(Relation relation, const ItemPointerData *tid,
CommandId cid, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart);
+ TM_FailureData *tmfd, bool changingPart,
+ bool wal_logical);
extern void heap_finish_speculative(Relation relation, const ItemPointerData *tid);
extern void heap_abort_speculative(Relation relation, const ItemPointerData *tid);
extern TM_Result heap_update(Relation relation, const ItemPointerData *otid,
HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
TM_FailureData *tmfd, LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes);
+ TU_UpdateIndexes *update_indexes, bool wal_logical);
extern TM_Result heap_lock_tuple(Relation relation, HeapTuple tuple,
CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy,
bool follow_updates,
diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h
index 16c2b2e3c9c..2cc49fd48de 100644
--- a/src/include/access/heapam_xlog.h
+++ b/src/include/access/heapam_xlog.h
@@ -104,6 +104,8 @@
#define XLH_DELETE_CONTAINS_OLD_KEY (1<<2)
#define XLH_DELETE_IS_SUPER (1<<3)
#define XLH_DELETE_IS_PARTITION_MOVE (1<<4)
+/* See heap_delete() */
+#define XLH_DELETE_NO_LOGICAL (1<<5)
/* convenience macro for checking whether any form of old tuple was logged */
#define XLH_DELETE_CONTAINS_OLD \
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 2fa790b6bf5..d8f76d325f9 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -22,6 +22,7 @@
#include "access/xact.h"
#include "commands/vacuum.h"
#include "executor/tuptable.h"
+#include "replication/logical.h"
#include "storage/read_stream.h"
#include "utils/rel.h"
#include "utils/snapshot.h"
@@ -629,6 +630,8 @@ typedef struct TableAmRoutine
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1646,6 +1649,10 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator)
* not needed for the relation's AM
* - *xid_cutoff - ditto
* - *multi_cutoff - ditto
+ * - snapshot - if != NULL, ignore data changes done by transactions that this
+ * (MVCC) snapshot considers still in-progress or in the future.
+ * - decoding_ctx - logical decoding context, to capture concurrent data
+ * changes.
*
* Output parameters:
* - *xid_cutoff - rel's new relfrozenxid value, may be invalid
@@ -1658,6 +1665,8 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1666,6 +1675,7 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
{
OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex,
use_sort, OldestXmin,
+ snapshot, decoding_ctx,
xid_cutoff, multi_cutoff,
num_tuples, tups_vacuumed,
tups_recently_dead);
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 652542e8e65..b43a1740053 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -13,10 +13,15 @@
#ifndef CLUSTER_H
#define CLUSTER_H
+#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
+#include "replication/logical.h"
#include "storage/lock.h"
+#include "storage/relfilelocator.h"
#include "utils/relcache.h"
+#include "utils/resowner.h"
+#include "utils/tuplestore.h"
/* flag bits for ClusterParams->options */
@@ -25,6 +30,8 @@
#define CLUOPT_RECHECK_ISCLUSTERED 0x04 /* recheck relation state for
* indisclustered */
#define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */
+#define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */
+
/* options for CLUSTER */
typedef struct ClusterParams
@@ -33,14 +40,94 @@ typedef struct ClusterParams
} ClusterParams;
+/*
+ * The following definitions are used by REPACK CONCURRENTLY.
+ */
+
+extern RelFileLocator repacked_rel_locator;
+extern RelFileLocator repacked_rel_toast_locator;
+
+typedef enum
+{
+ CHANGE_INSERT,
+ CHANGE_UPDATE_OLD,
+ CHANGE_UPDATE_NEW,
+ CHANGE_DELETE
+} ConcurrentChangeKind;
+
+typedef struct ConcurrentChange
+{
+ /* See the enum above. */
+ ConcurrentChangeKind kind;
+
+ /*
+ * The actual tuple.
+ *
+ * The tuple data follows the ConcurrentChange structure. Before use make
+ * sure the tuple is correctly aligned (ConcurrentChange can be stored as
+ * bytea) and that tuple->t_data is fixed.
+ */
+ HeapTupleData tup_data;
+} ConcurrentChange;
+
+#define SizeOfConcurrentChange (offsetof(ConcurrentChange, tup_data) + \
+ sizeof(HeapTupleData))
+
+/*
+ * Logical decoding state.
+ *
+ * Here we store the data changes that we decode from WAL while the table
+ * contents is being copied to a new storage. Also the necessary metadata
+ * needed to apply these changes to the table is stored here.
+ */
+typedef struct RepackDecodingState
+{
+ /* The relation whose changes we're decoding. */
+ Oid relid;
+
+ /* Replication slot name. */
+ NameData slotname;
+
+ /*
+ * Decoded changes are stored here. Although we try to avoid excessive
+ * batches, it can happen that the changes need to be stored to disk. The
+ * tuplestore does this transparently.
+ */
+ Tuplestorestate *tstore;
+
+ /* The current number of changes in tstore. */
+ double nchanges;
+
+ /*
+ * Descriptor to store the ConcurrentChange structure serialized (bytea).
+ * We can't store the tuple directly because tuplestore only supports
+ * minimum tuple and we may need to transfer OID system column from the
+ * output plugin. Also we need to transfer the change kind, so it's better
+ * to put everything in the structure than to use 2 tuplestores "in
+ * parallel".
+ */
+ TupleDesc tupdesc_change;
+
+ /* Tuple descriptor needed to update indexes. */
+ TupleDesc tupdesc;
+
+ /* Slot to retrieve data from tstore. */
+ TupleTableSlot *tsslot;
+
+ ResourceOwner resowner;
+} RepackDecodingState;
+
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid indexOid,
- ClusterParams *params);
+ ClusterParams *params, bool isTopLevel);
extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid,
LOCKMODE lockmode);
extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_internal);
+extern void repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
+ XLogRecPtr end_of_wal);
+
extern Oid make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
char relpersistence, LOCKMODE lockmode);
extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
@@ -48,6 +135,7 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
bool swap_toast_by_content,
bool check_constraints,
bool is_internal,
+ bool reindex,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence);
diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h
index 8d68bcbef95..18cb482ac26 100644
--- a/src/include/commands/progress.h
+++ b/src/include/commands/progress.h
@@ -86,10 +86,12 @@
#define PROGRESS_REPACK_PHASE 1
#define PROGRESS_REPACK_INDEX_RELID 2
#define PROGRESS_REPACK_HEAP_TUPLES_SCANNED 3
-#define PROGRESS_REPACK_HEAP_TUPLES_WRITTEN 4
-#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 5
-#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 6
-#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 7
+#define PROGRESS_REPACK_HEAP_TUPLES_INSERTED 4
+#define PROGRESS_REPACK_HEAP_TUPLES_UPDATED 5
+#define PROGRESS_REPACK_HEAP_TUPLES_DELETED 6
+#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 7
+#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 8
+#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 9
/*
* Phases of repack (as advertised via PROGRESS_REPACK_PHASE).
@@ -98,9 +100,10 @@
#define PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP 2
#define PROGRESS_REPACK_PHASE_SORT_TUPLES 3
#define PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP 4
-#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 5
-#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 6
-#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 7
+#define PROGRESS_REPACK_PHASE_CATCH_UP 5
+#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 6
+#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 7
+#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 8
/* Progress parameters for CREATE INDEX */
/* 3, 4 and 5 reserved for "waitfor" metrics */
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 6d4d2d1814c..802fc4b0823 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,6 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
extern void SnapBuildSnapDecRefcount(Snapshot snap);
extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
+extern Snapshot SnapBuildInitialSnapshotForRepack(SnapBuild *builder);
extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
extern void SnapBuildClearExportedSnapshot(void);
diff --git a/src/include/storage/lockdefs.h b/src/include/storage/lockdefs.h
index 7f3ba0352f6..2739327b0da 100644
--- a/src/include/storage/lockdefs.h
+++ b/src/include/storage/lockdefs.h
@@ -36,8 +36,8 @@ typedef int LOCKMODE;
#define AccessShareLock 1 /* SELECT */
#define RowShareLock 2 /* SELECT FOR UPDATE/FOR SHARE */
#define RowExclusiveLock 3 /* INSERT, UPDATE, DELETE */
-#define ShareUpdateExclusiveLock 4 /* VACUUM (non-FULL), ANALYZE, CREATE
- * INDEX CONCURRENTLY */
+#define ShareUpdateExclusiveLock 4 /* VACUUM (non-exclusive), ANALYZE, CREATE
+ * INDEX CONCURRENTLY, REPACK CONCURRENTLY */
#define ShareLock 5 /* CREATE INDEX (WITHOUT CONCURRENTLY) */
#define ShareRowExclusiveLock 6 /* like EXCLUSIVE MODE, but allows ROW
* SHARE */
diff --git a/src/include/utils/snapmgr.h b/src/include/utils/snapmgr.h
index f65f83c85cd..1f821fd2ccd 100644
--- a/src/include/utils/snapmgr.h
+++ b/src/include/utils/snapmgr.h
@@ -64,6 +64,8 @@ extern Snapshot GetLatestSnapshot(void);
extern void SnapshotSetCommandId(CommandId curcid);
extern Snapshot CopySnapshot(Snapshot snapshot);
+extern void FreeSnapshot(Snapshot snapshot);
+
extern Snapshot GetCatalogSnapshot(Oid relid);
extern Snapshot GetNonHistoricCatalogSnapshot(Oid relid);
extern void InvalidateCatalogSnapshot(void);
diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile
index c85034eb8cc..a9769f1d99f 100644
--- a/src/test/modules/injection_points/Makefile
+++ b/src/test/modules/injection_points/Makefile
@@ -14,12 +14,15 @@ REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress
ISOLATION = basic \
inplace \
+ repack \
+ repack_toast \
syscache-update-pruned \
index-concurrently-upsert \
index-concurrently-upsert-predicate \
reindex-concurrently-upsert \
reindex-concurrently-upsert-on-constraint \
reindex-concurrently-upsert-partitioned
+ISOLATION_OPTS = --temp-config $(top_srcdir)/src/test/modules/injection_points/logical.conf
# The injection points are cluster-wide, so disable installcheck
NO_INSTALLCHECK = 1
diff --git a/src/test/modules/injection_points/expected/repack.out b/src/test/modules/injection_points/expected/repack.out
new file mode 100644
index 00000000000..b575e9052ee
--- /dev/null
+++ b/src/test/modules/injection_points/expected/repack.out
@@ -0,0 +1,113 @@
+Parsed test spec with 2 sessions
+
+starting permutation: wait_before_lock change_existing change_new change_subxact1 change_subxact2 check2 wakeup_before_lock check1
+injection_points_attach
+-----------------------
+
+(1 row)
+
+step wait_before_lock:
+ REPACK (CONCURRENTLY) repack_test USING INDEX repack_test_pkey;
+ <waiting ...>
+step change_existing:
+ UPDATE repack_test SET i=10 where i=1;
+ UPDATE repack_test SET j=20 where i=2;
+ UPDATE repack_test SET i=30 where i=3;
+ UPDATE repack_test SET i=40 where i=30;
+ DELETE FROM repack_test WHERE i=4;
+
+step change_new:
+ INSERT INTO repack_test(i, j) VALUES (5, 5), (6, 6), (7, 7), (8, 8);
+ UPDATE repack_test SET i=50 where i=5;
+ UPDATE repack_test SET j=60 where i=6;
+ DELETE FROM repack_test WHERE i=7;
+
+step change_subxact1:
+ BEGIN;
+ INSERT INTO repack_test(i, j) VALUES (100, 100);
+ SAVEPOINT s1;
+ UPDATE repack_test SET i=101 where i=100;
+ SAVEPOINT s2;
+ UPDATE repack_test SET i=102 where i=101;
+ COMMIT;
+
+step change_subxact2:
+ BEGIN;
+ SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 110);
+ ROLLBACK TO SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 111);
+ COMMIT;
+
+step check2:
+ INSERT INTO relfilenodes(node)
+ SELECT relfilenode FROM pg_class WHERE relname='repack_test';
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+
+ i| j
+---+---
+ 2| 20
+ 6| 60
+ 8| 8
+ 10| 1
+ 40| 3
+ 50| 5
+102|100
+110|111
+(8 rows)
+
+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_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ SELECT count(*)
+ FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j)
+ WHERE d1.i ISNULL OR d2.i ISNULL;
+
+count
+-----
+ 2
+(1 row)
+
+ i| j
+---+---
+ 2| 20
+ 6| 60
+ 8| 8
+ 10| 1
+ 40| 3
+ 50| 5
+102|100
+110|111
+(8 rows)
+
+count
+-----
+ 0
+(1 row)
+
+injection_points_detach
+-----------------------
+
+(1 row)
+
diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out
new file mode 100644
index 00000000000..4f866a74e32
--- /dev/null
+++ b/src/test/modules/injection_points/expected/repack_toast.out
@@ -0,0 +1,64 @@
+Parsed test spec with 2 sessions
+
+starting permutation: wait_before_lock change check2 wakeup_before_lock check1
+injection_points_attach
+-----------------------
+
+(1 row)
+
+step wait_before_lock:
+ REPACK (CONCURRENTLY) repack_test;
+ <waiting ...>
+step change:
+ UPDATE repack_test SET j=get_long_string() where i=2;
+ DELETE FROM repack_test WHERE i=3;
+ INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+
+step check2:
+ INSERT INTO relfilenodes(node)
+ SELECT c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+
+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 c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ SELECT count(*)
+ FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j)
+ WHERE d1.i ISNULL OR d2.i ISNULL;
+
+count
+-----
+ 4
+(1 row)
+
+count
+-----
+ 0
+(1 row)
+
+injection_points_detach
+-----------------------
+
+(1 row)
+
diff --git a/src/test/modules/injection_points/logical.conf b/src/test/modules/injection_points/logical.conf
new file mode 100644
index 00000000000..e3d257315fa
--- /dev/null
+++ b/src/test/modules/injection_points/logical.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build
index 8d6f662040d..b72bfb8ff06 100644
--- a/src/test/modules/injection_points/meson.build
+++ b/src/test/modules/injection_points/meson.build
@@ -45,6 +45,8 @@ tests += {
'specs': [
'basic',
'inplace',
+ 'repack',
+ 'repack_toast',
'syscache-update-pruned',
'index-concurrently-upsert',
'index-concurrently-upsert-predicate',
@@ -55,5 +57,7 @@ tests += {
'runningcheck': false, # see syscache-update-pruned
# Some tests wait for all snapshots, so avoid parallel execution
'runningcheck-parallel': false,
+ # 'repack' requires wal_level = 'logical'.
+ 'regress_args': ['--temp-config', files('logical.conf')],
},
}
diff --git a/src/test/modules/injection_points/specs/repack.spec b/src/test/modules/injection_points/specs/repack.spec
new file mode 100644
index 00000000000..d727a9b056b
--- /dev/null
+++ b/src/test/modules/injection_points/specs/repack.spec
@@ -0,0 +1,142 @@
+# REPACK (CONCURRENTLY) ... USING INDEX ...;
+setup
+{
+ CREATE EXTENSION injection_points;
+
+ CREATE TABLE repack_test(i int PRIMARY KEY, j int);
+ INSERT INTO repack_test(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_test;
+ 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_test USING INDEX repack_test_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_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ 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 change_existing
+{
+ UPDATE repack_test SET i=10 where i=1;
+ UPDATE repack_test SET j=20 where i=2;
+ UPDATE repack_test SET i=30 where i=3;
+ UPDATE repack_test SET i=40 where i=30;
+ DELETE FROM repack_test WHERE i=4;
+}
+# Insert new rows and UPDATE / DELETE some of them. Again, update both key and
+# non-key column.
+step change_new
+{
+ INSERT INTO repack_test(i, j) VALUES (5, 5), (6, 6), (7, 7), (8, 8);
+ UPDATE repack_test SET i=50 where i=5;
+ UPDATE repack_test SET j=60 where i=6;
+ DELETE FROM repack_test WHERE i=7;
+}
+
+# When applying concurrent data changes, we should see the effects of an
+# in-progress subtransaction.
+#
+# XXX Not sure this test is useful now - it was designed for the patch that
+# preserves tuple visibility and which therefore modifies
+# TransactionIdIsCurrentTransactionId().
+step change_subxact1
+{
+ BEGIN;
+ INSERT INTO repack_test(i, j) VALUES (100, 100);
+ SAVEPOINT s1;
+ UPDATE repack_test SET i=101 where i=100;
+ SAVEPOINT s2;
+ UPDATE repack_test SET i=102 where i=101;
+ COMMIT;
+}
+
+# When applying concurrent data changes, we should not see the effects of a
+# rolled back subtransaction.
+#
+# XXX Is this test useful? See above.
+step change_subxact2
+{
+ BEGIN;
+ SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 110);
+ ROLLBACK TO SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 111);
+ COMMIT;
+}
+
+# Check the table from the perspective of s2.
+step check2
+{
+ INSERT INTO relfilenodes(node)
+ SELECT relfilenode FROM pg_class WHERE relname='repack_test';
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+}
+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
+ change_existing
+ change_new
+ change_subxact1
+ change_subxact2
+ check2
+ wakeup_before_lock
+ check1
diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec
new file mode 100644
index 00000000000..b48abf21450
--- /dev/null
+++ b/src/test/modules/injection_points/specs/repack_toast.spec
@@ -0,0 +1,105 @@
+# REPACK (CONCURRENTLY);
+#
+# Test handling of TOAST. At the same time, no tuplesort.
+setup
+{
+ CREATE EXTENSION injection_points;
+
+ -- Return a string that needs to be TOASTed.
+ CREATE FUNCTION get_long_string()
+ RETURNS text
+ LANGUAGE sql as $$
+ SELECT string_agg(chr(65 + trunc(25 * random())::int), '')
+ FROM generate_series(1, 2048) s(x);
+ $$;
+
+ CREATE TABLE repack_test(i int PRIMARY KEY, j text);
+ INSERT INTO repack_test(i, j) VALUES (1, get_long_string()),
+ (2, get_long_string()), (3, get_long_string());
+
+ CREATE TABLE relfilenodes(node oid);
+
+ CREATE TABLE data_s1(i int, j text);
+ CREATE TABLE data_s2(i int, j text);
+}
+
+teardown
+{
+ DROP TABLE repack_test;
+ DROP EXTENSION injection_points;
+ DROP FUNCTION get_long_string();
+
+ 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_test;
+}
+# 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 c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ 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
+step change
+{
+ UPDATE repack_test SET j=get_long_string() where i=2;
+ DELETE FROM repack_test WHERE i=3;
+ INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+}
+# Check the table from the perspective of s2.
+step check2
+{
+ INSERT INTO relfilenodes(node)
+ SELECT c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+}
+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
+ change
+ check2
+ wakeup_before_lock
+ check1
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index eb90fd3de5f..88da9ef75b4 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -2012,7 +2012,7 @@ pg_stat_progress_cluster| SELECT pid,
phase,
repack_index_relid AS cluster_index_relid,
heap_tuples_scanned,
- heap_tuples_written,
+ (heap_tuples_inserted + heap_tuples_updated) AS heap_tuples_written,
heap_blks_total,
heap_blks_scanned,
index_rebuild_count
@@ -2092,17 +2092,20 @@ pg_stat_progress_repack| SELECT s.pid,
WHEN 2 THEN 'index scanning heap'::text
WHEN 3 THEN 'sorting tuples'::text
WHEN 4 THEN 'writing new heap'::text
- WHEN 5 THEN 'swapping relation files'::text
- WHEN 6 THEN 'rebuilding index'::text
- WHEN 7 THEN 'performing final cleanup'::text
+ WHEN 5 THEN 'catch-up'::text
+ WHEN 6 THEN 'swapping relation files'::text
+ WHEN 7 THEN 'rebuilding index'::text
+ WHEN 8 THEN 'performing final cleanup'::text
ELSE NULL::text
END AS phase,
(s.param3)::oid AS repack_index_relid,
s.param4 AS heap_tuples_scanned,
- s.param5 AS heap_tuples_written,
- s.param6 AS heap_blks_total,
- s.param7 AS heap_blks_scanned,
- s.param8 AS index_rebuild_count
+ s.param5 AS heap_tuples_inserted,
+ s.param6 AS heap_tuples_updated,
+ s.param7 AS heap_tuples_deleted,
+ s.param8 AS heap_blks_total,
+ s.param9 AS heap_blks_scanned,
+ s.param10 AS index_rebuild_count
FROM (pg_stat_get_progress_info('REPACK'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
LEFT JOIN pg_database d ON ((s.datid = d.oid)));
pg_stat_progress_vacuum| SELECT s.pid,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 4f3c7c160a6..3139b14e85f 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -411,6 +411,7 @@ CatCacheHeader
CatalogId
CatalogIdMapEntry
CatalogIndexState
+ChangeDest
ChangeVarNodes_callback
ChangeVarNodes_context
CheckPoint
@@ -487,6 +488,8 @@ CompressFileHandle
CompressionLocation
CompressorState
ComputeXidHorizonsResult
+ConcurrentChange
+ConcurrentChangeKind
ConditionVariable
ConditionVariableMinimallyPadded
ConditionalStack
@@ -1264,6 +1267,7 @@ IndexElem
IndexFetchHeapData
IndexFetchTableData
IndexInfo
+IndexInsertState
IndexList
IndexOnlyScan
IndexOnlyScanState
@@ -2558,6 +2562,7 @@ ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepOriginId
RepackCommand
+RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
ReplaceVarsFromTargetList_context
--
2.47.3
From 32accb96480ddf42847ae23f30f23636d64eeb50 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 6/6] Use multiple snapshots to copy the data.
REPACK (CONCURRENTLY) does not prevent applications from using the table that
is being processed, however it can prevent the xmin horizon from advancing and
thus restrict VACUUM for the whole database. This patch adds the ability to
use particular snapshot only for certain range of pages. Each time that number
of pages is processed, a new snapshot is built, which supposedly has its xmin
higher than the previous snapshot.
The data copying works as follows:
1. Have the logical decoding system build a snapshot S0 for range R0 at
LSN0. This snapshot sees all the data changes whose commit records have
LSN < LSN0.
2. Copy the pages in that range to the new relation. The changes not visible
to the snapshot (because their transactions are still running) will
appear in the output of the logical decoding system as soon as their
commit records appear in WAL.
3. Perform logical decoding of all changes we find in WAL for the table
we're repacking, put them aside and remember that out of these we can
only apply those that affect the range R0 in the old
relation. (Naturally, we cannot apply ones that belong to other pages
because it's impossible to UPDATE / DELETE a row in the new relation if
it hasn't been copied yet.) Once the decoding is done, consider LSN1 to
be the position of the end of the last WAL record decoded.
4. Build a new snapshot S1 at position LSN1, i.e. one that sees all the data
whose commit records are at WAL positions < LSN1. Use this snapshot to
copy the range of pages R1.
5. Perform logical decoding like in step 3, but remember, that out of this
next set, only changes belonging to ranges R0 *and* R1 in the old table
can be applied.
6. etc
Note that the changes decoded above should not be applied to the new relation
until the whole relation has been copied. The point is that we need "identity
index" to apply UPDATE and DELETE statements, and bulk creation of indexes on
the already copied heap is probably better than retail insertions during the
copying.
Special attention needs to be paid to UPDATES that span page ranges. For
example, if the old tuple is in range R0, but the new tuple is in R1, and R1
hasn't been copied yet, we only DELETE the old version from the new
relation. The new version will be handled during processing of range R1. The
snapshot S1 will be based on WAL position following that UPDATE, so it'll see
the new tuple if its transaction's commit record is at WAL position lower than
the position where we built the snapshot. On the other hand, if the commit
record appears at higher position than the that of the snapshot, the
corresponding INSERT will be decoded and replayed sometime later: once the
scan of R1 started, changes of tuples belonging to it are no longer filtered
out.
Likewise, if the old tuple is in range R1 (not yet copied) but the new tuple
is in R0, we only perform INSERT on the new relation. The deletion of the old
version will either be visible to the snapshot S1 (i.e. the snapshot won't see
the old version), or replayed later.
This approach introduces one limitation though: if the USING INDEX clause is
specified, an explicit sort is always used. Index scan wouldn't work because
it does not return the tuples sorted by CTID. That way we wouldn't be able to
split the copying into ranges of pages. I'm not sure it's serious. If REPACK
runs concurrently and does not restrict VACUUM, the execution time should not
be critical.
A new GUC repack_snapshot_after can be used to set the number of pages per
snapshot. It's currently classified as DEVELOPER_OPTIONS and may be replaced
by a constant after enough evaluation is done.
---
src/backend/access/heap/heapam_handler.c | 144 ++++-
src/backend/commands/cluster.c | 561 +++++++++++++-----
src/backend/replication/logical/decode.c | 47 +-
src/backend/replication/logical/logical.c | 30 +-
.../replication/logical/reorderbuffer.c | 50 ++
src/backend/replication/logical/snapbuild.c | 27 +-
.../pgoutput_repack/pgoutput_repack.c | 2 +
src/backend/utils/misc/guc_parameters.dat | 10 +
src/backend/utils/misc/guc_tables.c | 1 +
src/include/access/tableam.h | 14 +-
src/include/commands/cluster.h | 65 ++
src/include/replication/logical.h | 2 +-
src/include/replication/reorderbuffer.h | 1 +
src/include/replication/snapbuild.h | 2 +-
src/tools/pgindent/typedefs.list | 3 +-
15 files changed, 771 insertions(+), 188 deletions(-)
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index cb09e6fd1dc..b87fad605e4 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -33,6 +33,7 @@
#include "catalog/index.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
+#include "commands/cluster.h"
#include "commands/progress.h"
#include "executor/executor.h"
#include "miscadmin.h"
@@ -686,12 +687,12 @@ static void
heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
Relation OldIndex, bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead)
+ double *tups_recently_dead,
+ void *tableam_data)
{
RewriteState rwstate = NULL;
IndexScanDesc indexScan;
@@ -707,7 +708,10 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
bool *isnull;
BufferHeapTupleTableSlot *hslot;
BlockNumber prev_cblock = InvalidBlockNumber;
- bool concurrent = snapshot != NULL;
+ ConcurrentChangeContext *ctx = (ConcurrentChangeContext *) tableam_data;
+ bool concurrent = ctx != NULL;
+ Snapshot snapshot = NULL;
+ BlockNumber range_end = InvalidBlockNumber;
/* Remember if it's a system catalog */
is_system_catalog = IsSystemRelation(OldHeap);
@@ -744,8 +748,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* that still need to be copied, we scan with SnapshotAny and use
* HeapTupleSatisfiesVacuum for the visibility test.
*
- * In the CONCURRENTLY case, we do regular MVCC visibility tests, using
- * the snapshot passed by the caller.
+ * In the CONCURRENTLY case, we do regular MVCC visibility tests. The
+ * snapshot changes several times during the scan so that we do not block
+ * the progress of the xmin horizon for VACUUM too much.
*/
if (OldIndex != NULL && !use_sort)
{
@@ -773,10 +778,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP);
- tableScan = table_beginscan(OldHeap,
- snapshot ? snapshot : SnapshotAny,
- 0, (ScanKey) NULL);
+ tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL);
heapScan = (HeapScanDesc) tableScan;
+
+ /*
+ * In CONCURRENTLY mode we scan the table by ranges of blocks and the
+ * algorithm below expects forward direction. (No other direction
+ * should be set here regardless concurrently anyway.)
+ */
+ Assert(heapScan->rs_dir == ForwardScanDirection || !concurrent);
indexScan = NULL;
/* Set total heap blocks */
@@ -787,6 +797,24 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
slot = table_slot_create(OldHeap, NULL);
hslot = (BufferHeapTupleTableSlot *) slot;
+ if (concurrent)
+ {
+ /*
+ * Do not block the progress of xmin horizons.
+ *
+ * TODO Analyze thoroughly if this might have bad consequences.
+ */
+ PopActiveSnapshot();
+ InvalidateCatalogSnapshot();
+
+ /*
+ * Wait until the worker has the initial snapshot and retrieve it.
+ */
+ snapshot = repack_get_snapshot(ctx);
+
+ PushActiveSnapshot(snapshot);
+ }
+
/*
* Scan through the OldHeap, either in OldIndex order or sequentially;
* copy each tuple into the NewHeap, or transiently to the tuplesort
@@ -803,6 +831,13 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
if (indexScan != NULL)
{
+ /*
+ * Index scan should not be used in the CONCURRENTLY case because
+ * it returns tuples in random order, so we could not split the
+ * scan into a series of page ranges.
+ */
+ Assert(!concurrent);
+
if (!index_getnext_slot(indexScan, ForwardScanDirection, slot))
break;
@@ -824,6 +859,18 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
*/
pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED,
heapScan->rs_nblocks);
+
+ if (concurrent)
+ {
+ PopActiveSnapshot();
+
+ /*
+ * For the last range, there are no restriction on block
+ * numbers, so the concurrent data changes pertaining to
+ * this range can decoded (and applied) anytime after this
+ * loop.
+ */
+ }
break;
}
@@ -922,6 +969,75 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
continue;
}
}
+ else
+ {
+ BlockNumber blkno;
+ bool visible;
+
+ /*
+ * With CONCURRENTLY, we use each snapshot only for certain range
+ * of pages, so that VACUUM does not get block for too long. So
+ * first check if the tuple falls into the current range.
+ */
+ blkno = BufferGetBlockNumber(buf);
+
+ /* The first block of the scan? */
+ if (!BlockNumberIsValid(ctx->first_block))
+ {
+ Assert(!BlockNumberIsValid(range_end));
+
+ ctx->first_block = blkno;
+ range_end = repack_blocks_per_snapshot;
+ }
+ else
+ {
+ Assert(BlockNumberIsValid(range_end));
+
+ /* End of the current range? */
+ if (blkno >= range_end)
+ {
+ XLogRecPtr end_of_wal;
+
+ PopActiveSnapshot();
+
+ /*
+ * XXX It might be worth Assert(CatalogSnapshot == NULL)
+ * here, however that symbol is not external.
+ */
+
+ /*
+ * Decode all the concurrent data changes committed so far
+ * - these will be applicable to the current range.
+ */
+ end_of_wal = GetFlushRecPtr(NULL);
+ repack_get_concurrent_changes(ctx, end_of_wal, range_end,
+ true, false);
+
+ /*
+ * Define the next range.
+ */
+ range_end = blkno + repack_blocks_per_snapshot;
+
+ /*
+ * Get the snapshot for the next range - it should have
+ * been built at the position right after the last change
+ * decoded. Data present in the next range of blocks will
+ * either be visible to the snapshot or appear in the next
+ * batch of decoded changes.
+ */
+ snapshot = repack_get_snapshot(ctx);
+ PushActiveSnapshot(snapshot);
+ }
+ }
+
+ /* Finally check the tuple visibility. */
+ LockBuffer(buf, BUFFER_LOCK_SHARE);
+ visible = HeapTupleSatisfiesVisibility(tuple, snapshot, buf);
+ LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+
+ if (!visible)
+ continue;
+ }
*num_tuples += 1;
if (tuplesort != NULL)
@@ -956,6 +1072,18 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
}
}
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ /* Decode the changes belonging to the last range. */
+ end_of_wal = GetFlushRecPtr(NULL);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber,
+ false, false);
+
+ PushActiveSnapshot(GetTransactionSnapshot());
+ }
+
if (indexScan != NULL)
index_endscan(indexScan);
if (tableScan != NULL)
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index b0383c1375f..3eb642b996d 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -110,38 +110,27 @@ typedef struct
RelFileLocator repacked_rel_locator = {.relNumber = InvalidOid};
RelFileLocator repacked_rel_toast_locator = {.relNumber = InvalidOid};
-/*
- * Everything we need to call ExecInsertIndexTuples().
- */
-typedef struct IndexInsertState
-{
- ResultRelInfo *rri;
- EState *estate;
-} IndexInsertState;
-
/* The WAL segment being decoded. */
static XLogSegNo repack_current_segment = 0;
/*
- * Information needed to apply concurrent data changes.
+ * When REPACK (CONCURRENTLY) copies data to the new heap, a new snapshot is
+ * built after processing this many pages.
*/
-typedef struct ChangeDest
-{
- /* The relation the changes are applied to. */
- Relation rel;
+int repack_blocks_per_snapshot = 1024;
- /*
- * The following is needed to find the existing tuple if the change is
- * UPDATE or DELETE. 'ident_key' should have all the fields except for
- * 'sk_argument' initialized.
- */
- Relation ident_index;
- ScanKey ident_key;
- int ident_key_nentries;
+/*
+ * Remember here to which pages should applied to changes recorded in given
+ * file.
+ */
+typedef struct RepackApplyRange
+{
+ /* The first block of the next range. */
+ BlockNumber end;
- /* Needed to update indexes of rel_dst. */
- IndexInsertState *iistate;
-} ChangeDest;
+ /* File containing the changes to be applied to blocks in this range. */
+ char *fname;
+} RepackApplyRange;
/*
* Layout of shared memory used for communication between backend and the
@@ -152,6 +141,9 @@ typedef struct DecodingWorkerShared
/* Is the decoding initialized? */
bool initialized;
+ /* Set to request a snapshot. */
+ bool snapshot_requested;
+
/*
* Once the worker has reached this LSN, it should close the current
* output file and either create a new one or exit, according to the field
@@ -159,20 +151,25 @@ typedef struct DecodingWorkerShared
* the WAL available and keep checking this field. It is ok if the worker
* had already decoded records whose LSN is >= lsn_upto before this field
* has been set.
+ *
+ * Set a valid LSN to request data changes.
*/
XLogRecPtr lsn_upto;
+#define WORKER_RESPONSE_SNAPSHOT 0x1
+#define WORKER_RESPONSE_CHANGES 0x2
+ /* Which kind of data is ready? */
+ int response;;
+
/* Exit after closing the current file? */
bool done;
/* The output is stored here. */
SharedFileSet sfs;
- /* Can backend read the file contents? */
- bool sfs_valid;
-
/* Number of the last file exported by the worker. */
- int last_exported;
+ int last_exported_changes;
+ int last_exported_snapshot;
/* Synchronize access to the fields above. */
slock_t mutex;
@@ -214,26 +211,14 @@ typedef struct DecodingWorkerShared
* the fileset name.)
*/
static inline void
-DecodingWorkerFileName(char *fname, Oid relid, uint32 seq)
+DecodingWorkerFileName(char *fname, Oid relid, uint32 seq, bool snapshot)
{
- snprintf(fname, MAXPGPATH, "%u-%u", relid, seq);
+ if (!snapshot)
+ snprintf(fname, MAXPGPATH, "%u-%u", relid, seq);
+ else
+ snprintf(fname, MAXPGPATH, "%u-%u-snapshot", relid, seq);
}
-/*
- * Backend-local information to control the decoding worker.
- */
-typedef struct DecodingWorker
-{
- /* The worker. */
- BackgroundWorkerHandle *handle;
-
- /* DecodingWorkerShared is in this segment. */
- dsm_segment *seg;
-
- /* Handle of the error queue. */
- shm_mq_handle *error_mqh;
-} DecodingWorker;
-
/* Pointer to currently running decoding worker. */
static DecodingWorker *decoding_worker = NULL;
@@ -250,11 +235,11 @@ static void check_repack_concurrently_requirements(Relation rel);
static void rebuild_relation(Relation OldHeap, Relation index, bool verbose,
bool concurrent);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot,
bool verbose,
bool *pSwapToastByContent,
TransactionId *pFreezeXid,
- MultiXactId *pCutoffMulti);
+ MultiXactId *pCutoffMulti,
+ ConcurrentChangeContext *ctx);
static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
MemoryContext permcxt);
static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -264,9 +249,12 @@ static bool cluster_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
static LogicalDecodingContext *setup_logical_decoding(Oid relid);
-static bool decode_concurrent_changes(LogicalDecodingContext *ctx,
+static bool decode_concurrent_changes(LogicalDecodingContext *decoding_ctx,
DecodingWorkerShared *shared);
-static void apply_concurrent_changes(BufFile *file, ChangeDest *dest);
+static void apply_concurrent_changes(ConcurrentChangeContext *ctx);
+static void apply_concurrent_changes_file(ConcurrentChangeContext *ctx,
+ BufFile *file,
+ BlockNumber range_end);
static void apply_concurrent_insert(Relation rel, HeapTuple tup,
IndexInsertState *iistate,
TupleTableSlot *index_slot);
@@ -275,12 +263,14 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup,
IndexInsertState *iistate,
TupleTableSlot *index_slot);
static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
-static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
+static bool is_tuple_in_block_range(HeapTuple tup, BlockNumber start,
+ BlockNumber end);
+static HeapTuple find_target_tuple(Relation rel,
+ ConcurrentChangeContext *ctx,
HeapTuple tup_key,
TupleTableSlot *ident_slot);
-static void process_concurrent_changes(XLogRecPtr end_of_wal,
- ChangeDest *dest,
- bool done);
+static void repack_add_block_range(ConcurrentChangeContext *ctx,
+ BlockNumber end, char *fname);
static IndexInsertState *get_index_insert_state(Relation relation,
Oid ident_index_id,
Relation *ident_index_p);
@@ -291,7 +281,8 @@ static void cleanup_logical_decoding(LogicalDecodingContext *ctx);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
TransactionId frozenXid,
- MultiXactId cutoffMulti);
+ MultiXactId cutoffMulti,
+ ConcurrentChangeContext *ctx);
static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes);
static Relation process_single_relation(RepackStmt *stmt,
LOCKMODE lockmode,
@@ -302,9 +293,8 @@ static Oid determine_clustered_index(Relation rel, bool usingindex,
static void start_decoding_worker(Oid relid);
static void stop_decoding_worker(void);
static void repack_worker_internal(dsm_segment *seg);
-static void export_initial_snapshot(Snapshot snapshot,
- DecodingWorkerShared *shared);
-static Snapshot get_initial_snapshot(DecodingWorker *worker);
+static void export_snapshot(Snapshot snapshot,
+ DecodingWorkerShared *shared);
static void ProcessRepackMessage(StringInfo msg);
static const char *RepackCommandAsString(RepackCommand cmd);
@@ -1008,6 +998,15 @@ check_repack_concurrently_requirements(Relation rel)
RelationGetRelationName(rel)),
(errhint("Relation \"%s\" has no identity index.",
RelationGetRelationName(rel)))));
+
+ /*
+ * In the CONCURRENTLY mode we don't want to use the same snapshot
+ * throughout the whole processing, as it could block the progress of xmin
+ * horizon.
+ */
+ if (IsolationUsesXactSnapshot())
+ ereport(ERROR,
+ (errmsg("REPACK (CONCURRENTLY) does not support transaction isolation higher than READ COMMITTED")));
}
@@ -1038,7 +1037,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
bool swap_toast_by_content;
TransactionId frozenXid;
MultiXactId cutoffMulti;
- Snapshot snapshot = NULL;
+ ConcurrentChangeContext *ctx = NULL;
#if USE_ASSERT_CHECKING
LOCKMODE lmode;
@@ -1050,6 +1049,13 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
if (concurrent)
{
+ /*
+ * This is only needed here to gather the data changes and range
+ * information during the copying. The fields needed to apply the
+ * changes be filled later.
+ */
+ ctx = palloc0_object(ConcurrentChangeContext);
+
/*
* The worker needs to be member of the locking group we're the leader
* of. We ought to become the leader before the worker starts. The
@@ -1075,13 +1081,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
* REPACK CONCURRENTLY.
*/
start_decoding_worker(tableOid);
-
- /*
- * Wait until the worker has the initial snapshot and retrieve it.
- */
- snapshot = get_initial_snapshot(decoding_worker);
-
- PushActiveSnapshot(snapshot);
+ ctx->worker = decoding_worker;
}
/* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */
@@ -1105,21 +1105,25 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
NewHeap = table_open(OIDNewHeap, NoLock);
/* Copy the heap data into the new table in the desired order */
- copy_table_data(NewHeap, OldHeap, index, snapshot, verbose,
- &swap_toast_by_content, &frozenXid, &cutoffMulti);
-
- /* The historic snapshot won't be needed anymore. */
- if (snapshot)
+ if (concurrent)
{
- PopActiveSnapshot();
- UpdateActiveSnapshotCommandId();
+ ctx->first_block = InvalidBlockNumber;
+ ctx->block_ranges = NIL;
}
+ copy_table_data(NewHeap, OldHeap, index, verbose, &swap_toast_by_content,
+ &frozenXid, &cutoffMulti, ctx);
if (concurrent)
{
+ /*
+ * Make sure the active snapshot can see the data copied, so the rows
+ * can be updated / deleted.
+ */
+ UpdateActiveSnapshotCommandId();
+
Assert(!swap_toast_by_content);
rebuild_relation_finish_concurrent(NewHeap, OldHeap, index,
- frozenXid, cutoffMulti);
+ frozenXid, cutoffMulti, ctx);
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
@@ -1283,9 +1287,6 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
/*
* Do the physical copying of table data.
*
- * 'snapshot' and 'decoding_ctx': see table_relation_copy_for_cluster(). Pass
- * iff concurrent processing is required.
- *
* There are three output parameters:
* *pSwapToastByContent is set true if toast tables must be swapped by content.
* *pFreezeXid receives the TransactionId used as freeze cutoff point.
@@ -1293,8 +1294,9 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
*/
static void
copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot, bool verbose, bool *pSwapToastByContent,
- TransactionId *pFreezeXid, MultiXactId *pCutoffMulti)
+ bool verbose, bool *pSwapToastByContent,
+ TransactionId *pFreezeXid, MultiXactId *pCutoffMulti,
+ ConcurrentChangeContext *ctx)
{
Relation relRelation;
HeapTuple reltup;
@@ -1311,7 +1313,7 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
int elevel = verbose ? INFO : DEBUG2;
PGRUsage ru0;
char *nspname;
- bool concurrent = snapshot != NULL;
+ bool concurrent = ctx != NULL;
LOCKMODE lmode;
lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
@@ -1423,8 +1425,18 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
* provided, else plain seqscan.
*/
if (OldIndex != NULL && OldIndex->rd_rel->relam == BTREE_AM_OID)
- use_sort = plan_cluster_use_sort(RelationGetRelid(OldHeap),
- RelationGetRelid(OldIndex));
+ {
+ if (!concurrent)
+ use_sort = plan_cluster_use_sort(RelationGetRelid(OldHeap),
+ RelationGetRelid(OldIndex));
+ else
+
+ /*
+ * To use multiple snapshots, we need to process the table
+ * sequentially.
+ */
+ use_sort = true;
+ }
else
use_sort = false;
@@ -1453,11 +1465,11 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
* values (e.g. because the AM doesn't use freezing).
*/
table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort,
- cutoffs.OldestXmin, snapshot,
+ cutoffs.OldestXmin,
&cutoffs.FreezeLimit,
&cutoffs.MultiXactCutoff,
&num_tuples, &tups_vacuumed,
- &tups_recently_dead);
+ &tups_recently_dead, ctx);
/* return selected values to caller, get set as relfrozenxid/minmxid */
*pFreezeXid = cutoffs.FreezeLimit;
@@ -2610,6 +2622,7 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
DecodingWorkerShared *shared)
{
RepackDecodingState *dstate;
+ bool snapshot_requested;
XLogRecPtr lsn_upto;
bool done;
char fname[MAXPGPATH];
@@ -2617,11 +2630,14 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
dstate = (RepackDecodingState *) ctx->output_writer_private;
/* Open the output file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_changes + 1,
+ false);
dstate->file = BufFileCreateFileSet(&shared->sfs.fs, fname);
SpinLockAcquire(&shared->mutex);
lsn_upto = shared->lsn_upto;
+ snapshot_requested = shared->snapshot_requested;
done = shared->done;
SpinLockRelease(&shared->mutex);
@@ -2689,6 +2705,7 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
{
SpinLockAcquire(&shared->mutex);
lsn_upto = shared->lsn_upto;
+ snapshot_requested = shared->snapshot_requested;
/* 'done' should be set at the same time as 'lsn_upto' */
done = shared->done;
SpinLockRelease(&shared->mutex);
@@ -2710,28 +2727,108 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
*/
BufFileClose(dstate->file);
dstate->file = NULL;
+
+ /*
+ * Before publishing the data changes, export the snapshot too if
+ * requested. Publishing both at once makes sense because both are needed
+ * at the same time, and it's simpler.
+ */
+ if (snapshot_requested)
+ {
+ Snapshot snapshot;
+
+ snapshot = SnapBuildSnapshotForRepack(ctx->snapshot_builder);
+ export_snapshot(snapshot, shared);
+
+ /*
+ * Adjust the replication slot's xmin so that VACUUM can do more work.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, snapshot->xmin, false);
+ FreeSnapshot(snapshot);
+ }
+ else
+ {
+ /*
+ * If data changes were requested but no following snapshot, we don't
+ * care about xmin horizon because the heap copying should be done by
+ * now.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, InvalidTransactionId,
+ false);
+
+ }
+
+ /* Now announce that the output is available. */
SpinLockAcquire(&shared->mutex);
shared->lsn_upto = InvalidXLogRecPtr;
- shared->sfs_valid = true;
- shared->last_exported++;
+ shared->response |= WORKER_RESPONSE_CHANGES;
+ shared->last_exported_changes++;
+ if (snapshot_requested)
+ {
+ shared->snapshot_requested = false;
+ shared->response |= WORKER_RESPONSE_SNAPSHOT;
+ shared->last_exported_snapshot++;
+ }
SpinLockRelease(&shared->mutex);
+
ConditionVariableSignal(&shared->cv);
return done;
}
/*
- * Apply changes stored in 'file'.
+ * Apply all concurrent changes.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeDest *dest)
+apply_concurrent_changes(ConcurrentChangeContext *ctx)
+{
+ DecodingWorkerShared *shared;
+ ListCell *lc;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ foreach(lc, ctx->block_ranges)
+ {
+ RepackApplyRange *range;
+ BufFile *file;
+
+ range = (RepackApplyRange *) lfirst(lc);
+
+ file = BufFileOpenFileSet(&shared->sfs.fs, range->fname, O_RDONLY,
+ false);
+
+ /*
+ * If range end is valid, the start should be as well.
+ */
+ Assert(!BlockNumberIsValid(range->end) ||
+ BlockNumberIsValid(ctx->first_block));
+
+ apply_concurrent_changes_file(ctx, file, range->end);
+ BufFileClose(file);
+
+ pfree(range->fname);
+ pfree(range);
+ }
+
+ /* Get ready for the next decoding. */
+ ctx->block_ranges = NIL;
+ ctx->first_block = InvalidBlockNumber;
+}
+
+/*
+ * Apply concurrent changes stored in 'file'.
+ */
+static void
+apply_concurrent_changes_file(ConcurrentChangeContext *ctx, BufFile *file,
+ BlockNumber range_end)
{
char kind;
uint32 t_len;
- Relation rel = dest->rel;
+ Relation rel = ctx->rel;
TupleTableSlot *index_slot,
*ident_slot;
HeapTuple tup_old = NULL;
+ bool check_range = BlockNumberIsValid(range_end);
/* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
index_slot = MakeSingleTupleTableSlot(RelationGetDescr(rel),
@@ -2759,8 +2856,8 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE);
BufFileReadExact(file, tup->t_data, t_len);
tup->t_len = t_len;
- ItemPointerSetInvalid(&tup->t_self);
- tup->t_tableOid = RelationGetRelid(dest->rel);
+ tup->t_tableOid = RelationGetRelid(ctx->rel);
+ BufFileReadExact(file, &tup->t_self, sizeof(tup->t_self));
if (kind == CHANGE_UPDATE_OLD)
{
@@ -2771,7 +2868,10 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
{
Assert(tup_old == NULL);
- apply_concurrent_insert(rel, tup, dest->iistate, index_slot);
+ if (!check_range ||
+ is_tuple_in_block_range(tup, ctx->first_block, range_end))
+ apply_concurrent_insert(rel, tup, ctx->iistate,
+ index_slot);
pfree(tup);
}
@@ -2792,16 +2892,52 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
/*
* Find the tuple to be updated or deleted.
*/
- tup_exist = find_target_tuple(rel, dest, tup_key, ident_slot);
- if (tup_exist == NULL)
- elog(ERROR, "failed to find target tuple");
+ if (!check_range ||
+ (is_tuple_in_block_range(tup_key, ctx->first_block,
+ range_end)))
+ {
+ /* The change needs to be applied to this tuple. */
+ tup_exist = find_target_tuple(rel, ctx, tup_key, ident_slot);
+ if (tup_exist == NULL)
+ elog(ERROR, "failed to find target tuple");
- if (kind == CHANGE_UPDATE_NEW)
- apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
- index_slot);
+ if (kind == CHANGE_DELETE)
+ apply_concurrent_delete(rel, tup_exist);
+ else
+ {
+ /* UPDATE */
+ if (!check_range || tup == tup_key ||
+ is_tuple_in_block_range(tup, ctx->first_block,
+ range_end))
+ /* The new tuple is in the same range. */
+ apply_concurrent_update(rel, tup, tup_exist,
+ ctx->iistate, index_slot);
+ else
+
+ /*
+ * The new key is in the other range, so only delete
+ * it from the current one. The new version should be
+ * visible to the snapshot that we'll use to copy the
+ * other block.
+ */
+ apply_concurrent_delete(rel, tup_exist);
+ }
+ }
else
- apply_concurrent_delete(rel, tup_exist);
-
+ {
+ /*
+ * The change belongs to another range, so we don't need to
+ * bother with the old tuple: the snapshot used for the other
+ * range won't see it, so it won't be copied. However, the new
+ * tuple still may need to go to the range we are checking. In
+ * that case, simply insert it there.
+ */
+ if (kind == CHANGE_UPDATE_NEW && tup != tup_key &&
+ is_tuple_in_block_range(tup, ctx->first_block,
+ range_end))
+ apply_concurrent_insert(rel, tup, ctx->iistate,
+ index_slot);
+ }
if (tup_old != NULL)
{
pfree(tup_old);
@@ -2940,6 +3076,33 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target)
pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1);
}
+/*
+ * Check if tuple originates from given range of blocks that have already been
+ * copied.
+ */
+static bool
+is_tuple_in_block_range(HeapTuple tup, BlockNumber start, BlockNumber end)
+{
+ BlockNumber blknum;
+
+ Assert(BlockNumberIsValid(start) && BlockNumberIsValid(end));
+
+ blknum = ItemPointerGetBlockNumber(&tup->t_self);
+ Assert(BlockNumberIsValid(blknum));
+
+ if (start < end)
+ {
+ return blknum >= start && blknum < end;
+ }
+ else
+ {
+ /* Has the scan position wrapped around? */
+ Assert(start > end);
+
+ return blknum >= start || blknum < end;
+ }
+}
+
/*
* Find the tuple to be updated or deleted.
*
@@ -2949,10 +3112,10 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target)
* it when he no longer needs the tuple returned.
*/
static HeapTuple
-find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
- TupleTableSlot *ident_slot)
+find_target_tuple(Relation rel, ConcurrentChangeContext *ctx,
+ HeapTuple tup_key, TupleTableSlot *ident_slot)
{
- Relation ident_index = dest->ident_index;
+ Relation ident_index = ctx->ident_index;
IndexScanDesc scan;
Form_pg_index ident_form;
int2vector *ident_indkey;
@@ -2960,14 +3123,14 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
/* XXX no instrumentation for now */
scan = index_beginscan(rel, ident_index, GetActiveSnapshot(),
- NULL, dest->ident_key_nentries, 0);
+ NULL, ctx->ident_key_nentries, 0);
/*
* Scan key is passed by caller, so it does not have to be constructed
* multiple times. Key entries have all fields initialized, except for
* sk_argument.
*/
- index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
+ index_rescan(scan, ctx->ident_key, ctx->ident_key_nentries, NULL, 0);
/* Info needed to retrieve key values from heap tuple. */
ident_form = ident_index->rd_index;
@@ -3002,15 +3165,22 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
}
/*
- * Decode and apply concurrent changes, up to (and including) the record whose
- * LSN is 'end_of_wal'.
+ * Get concurrent changes, up to (and including) the record whose LSN is
+ * 'end_of_wal', from the decoding worker. If 'range_end' is a valid block
+ * number, the changes should only be applied to blocks greater than or equal
+ * to ctx->first_block and lower than range_end.
+ *
+ * If 'request_snapshot' is true, the snapshot built at LSN following the last
+ * data change needs to be exported too.
*/
-static void
-process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
+extern void
+repack_get_concurrent_changes(ConcurrentChangeContext *ctx,
+ XLogRecPtr end_of_wal,
+ BlockNumber range_end,
+ bool request_snapshot, bool done)
{
DecodingWorkerShared *shared;
char fname[MAXPGPATH];
- BufFile *file;
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_CATCH_UP);
@@ -3019,6 +3189,8 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
SpinLockAcquire(&shared->mutex);
shared->lsn_upto = end_of_wal;
+ Assert(!shared->snapshot_requested);
+ shared->snapshot_requested = request_snapshot;
shared->done = done;
SpinLockRelease(&shared->mutex);
@@ -3030,32 +3202,49 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
ConditionVariablePrepareToSleep(&shared->cv);
for (;;)
{
- bool valid;
+ int response;
SpinLockAcquire(&shared->mutex);
- valid = shared->sfs_valid;
+ response = shared->response;
SpinLockRelease(&shared->mutex);
- if (valid)
+ if (response & WORKER_RESPONSE_CHANGES)
break;
ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
}
ConditionVariableCancelSleep();
- /* Open the file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
- file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, dest);
+ /*
+ * Remember the file name so we can apply the changes when appropriate.
+ * One particular reason to postpone the replay is that indexes haven't
+ * been built yet on the new heap.
+ */
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_changes,
+ false);
+ repack_add_block_range(ctx, range_end, fname);
/* No file is exported until the worker exports the next one. */
SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = false;
+ shared->response &= ~WORKER_RESPONSE_CHANGES;
+ Assert(XLogRecPtrIsInvalid(shared->lsn_upto));
SpinLockRelease(&shared->mutex);
+}
- BufFileClose(file);
+static void
+repack_add_block_range(ConcurrentChangeContext *ctx, BlockNumber end,
+ char *fname)
+{
+ RepackApplyRange *range;
+
+ range = palloc_object(RepackApplyRange);
+ range->end = end;
+ range->fname = pstrdup(fname);
+ ctx->block_ranges = lappend(ctx->block_ranges, range);
}
+
/*
* Initialize IndexInsertState for index specified by ident_index_id.
*
@@ -3198,7 +3387,8 @@ static void
rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
TransactionId frozenXid,
- MultiXactId cutoffMulti)
+ MultiXactId cutoffMulti,
+ ConcurrentChangeContext *ctx)
{
LOCKMODE lockmode_old PG_USED_FOR_ASSERTS_ONLY;
List *ind_oids_new;
@@ -3217,7 +3407,6 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation *ind_refs,
*ind_refs_p;
int nind;
- ChangeDest chgdst;
/* Like in cluster_rel(). */
lockmode_old = ShareUpdateExclusiveLock;
@@ -3274,11 +3463,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
(errmsg("identity index missing on the new relation")));
/* Gather information to apply concurrent changes. */
- chgdst.rel = NewHeap;
- chgdst.iistate = get_index_insert_state(NewHeap, ident_idx_new,
- &chgdst.ident_index);
- chgdst.ident_key = build_identity_key(ident_idx_new, OldHeap,
- &chgdst.ident_key_nentries);
+ ctx->rel = NewHeap;
+ ctx->iistate = get_index_insert_state(NewHeap, ident_idx_new,
+ &ctx->ident_index);
+ ctx->ident_key = build_identity_key(ident_idx_new, OldHeap,
+ &ctx->ident_key_nentries);
+
+ /*
+ * Replay the concurrent data changes gathered during heap copying. This
+ * had to wait until after the index build because the identity index is
+ * needed to apply UPDATE and DELETE changes.
+ */
+ apply_concurrent_changes(ctx);
/*
* During testing, wait for another backend to perform concurrent data
@@ -3296,11 +3492,13 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
end_of_wal = GetFlushRecPtr(NULL);
/*
- * Apply concurrent changes first time, to minimize the time we need to
- * hold AccessExclusiveLock. (Quite some amount of WAL could have been
+ * Decode and apply concurrent changes again, to minimize the time we need
+ * to hold AccessExclusiveLock. (Quite some amount of WAL could have been
* written during the data copying and index creation.)
*/
- process_concurrent_changes(end_of_wal, &chgdst, false);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber, false,
+ false);
+ apply_concurrent_changes(ctx);
/*
* Acquire AccessExclusiveLock on the table, its TOAST relation (if there
@@ -3397,10 +3595,13 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
end_of_wal = GetFlushRecPtr(NULL);
/*
- * Apply the concurrent changes again. Indicate that the decoding worker
- * won't be needed anymore.
+ * Decode and apply the concurrent changes again. Indicate that the
+ * decoding worker won't be needed anymore.
*/
- process_concurrent_changes(end_of_wal, &chgdst, true);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber, false,
+ true);
+ apply_concurrent_changes(ctx);
+
/* Remember info about rel before closing OldHeap */
relpersistence = OldHeap->rd_rel->relpersistence;
@@ -3451,8 +3652,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
table_close(NewHeap, NoLock);
/* Cleanup what we don't need anymore. (And close the identity index.) */
- pfree(chgdst.ident_key);
- free_index_insert_state(chgdst.iistate);
+ pfree(ctx->ident_key);
+ free_index_insert_state(ctx->iistate);
/*
* Swap the relations and their TOAST relations and TOAST indexes. This
@@ -3495,6 +3696,23 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
char *newName;
Relation ind;
+ /*
+ * Try to reduce the impact on VACUUM.
+ *
+ * The individual builds might still be a problem, but that's a
+ * separate issue.
+ *
+ * TODO Can we somehow use the fact that the new heap is not yet
+ * visible to other transaction, and thus cannot be vacuumed? Perhaps
+ * by preventing snapshots from setting MyProc->xmin temporarily. (All
+ * the snapshots that might have participated in the build, including
+ * the catalog snapshots, must not be used for other tables of
+ * course.)
+ */
+ PopActiveSnapshot();
+ InvalidateCatalogSnapshot();
+ PushActiveSnapshot(GetTransactionSnapshot());
+
ind_oid = lfirst_oid(lc);
ind = index_open(ind_oid, ShareUpdateExclusiveLock);
@@ -3534,11 +3752,15 @@ start_decoding_worker(Oid relid)
BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
seg = dsm_create(size, 0);
shared = (DecodingWorkerShared *) dsm_segment_address(seg);
+ shared->initialized = false;
shared->lsn_upto = InvalidXLogRecPtr;
shared->done = false;
+ /* Snapshot is the first thing we need from the worker. */
+ shared->snapshot_requested = true;
+ shared->response = 0;
SharedFileSetInit(&shared->sfs, seg);
- shared->sfs_valid = false;
- shared->last_exported = -1;
+ shared->last_exported_changes = -1;
+ shared->last_exported_snapshot = -1;
SpinLockInit(&shared->mutex);
shared->dbid = MyDatabaseId;
@@ -3747,7 +3969,10 @@ repack_worker_internal(dsm_segment *seg)
*/
SpinLockAcquire(&shared->mutex);
Assert(XLogRecPtrIsInvalid(shared->lsn_upto));
- Assert(!shared->sfs_valid);
+ Assert(shared->response == 0);
+ /* Initially we're expected to provide a snapshot and only that. */
+ Assert(shared->snapshot_requested &&
+ XLogRecPtrIsInvalid(shared->lsn_upto));
sfs = &shared->sfs;
SpinLockRelease(&shared->mutex);
@@ -3765,8 +3990,23 @@ repack_worker_internal(dsm_segment *seg)
ConditionVariableSignal(&shared->cv);
/* Build the initial snapshot and export it. */
- snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
- export_initial_snapshot(snapshot, shared);
+ snapshot = SnapBuildSnapshotForRepack(decoding_ctx->snapshot_builder);
+ export_snapshot(snapshot, shared);
+
+ /*
+ * Adjust the replication slot's xmin so that VACUUM can do more work.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, snapshot->xmin, false);
+ FreeSnapshot(snapshot);
+
+ /* Tell the backend that the file is available. */
+ SpinLockAcquire(&shared->mutex);
+ Assert(shared->snapshot_requested);
+ shared->snapshot_requested = false;
+ shared->response |= WORKER_RESPONSE_SNAPSHOT;
+ shared->last_exported_snapshot++;
+ SpinLockRelease(&shared->mutex);
+ ConditionVariableSignal(&shared->cv);
/*
* Only historic snapshots should be used now. Do not let us restrict the
@@ -3786,7 +4026,7 @@ repack_worker_internal(dsm_segment *seg)
* Make snapshot available to the backend that launched the decoding worker.
*/
static void
-export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
+export_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
{
char fname[MAXPGPATH];
BufFile *file;
@@ -3796,29 +4036,23 @@ export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
snap_size = EstimateSnapshotSpace(snapshot);
snap_space = (char *) palloc(snap_size);
SerializeSnapshot(snapshot, snap_space);
- FreeSnapshot(snapshot);
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_snapshot + 1,
+ true);
file = BufFileCreateFileSet(&shared->sfs.fs, fname);
/* To make restoration easier, write the snapshot size first. */
BufFileWrite(file, &snap_size, sizeof(snap_size));
BufFileWrite(file, snap_space, snap_size);
pfree(snap_space);
BufFileClose(file);
-
- /* Tell the backend that the file is available. */
- SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = true;
- shared->last_exported++;
- SpinLockRelease(&shared->mutex);
- ConditionVariableSignal(&shared->cv);
}
/*
- * Get the initial snapshot from the decoding worker.
+ * Get snapshot from the decoding worker.
*/
-static Snapshot
-get_initial_snapshot(DecodingWorker *worker)
+extern Snapshot
+repack_get_snapshot(ConcurrentChangeContext *ctx)
{
DecodingWorkerShared *shared;
char fname[MAXPGPATH];
@@ -3826,24 +4060,26 @@ get_initial_snapshot(DecodingWorker *worker)
Size snap_size;
char *snap_space;
Snapshot snapshot;
+ DecodingWorker *worker = ctx->worker;
shared = (DecodingWorkerShared *) dsm_segment_address(worker->seg);
/*
- * The worker needs to initialize the logical decoding, which usually
- * takes some time. Therefore it makes sense to prepare for the sleep
- * first.
+ * For the first snapshot request, the worker needs to initialize the
+ * logical decoding, which usually takes some time. Therefore it makes
+ * sense to prepare for the sleep first. Does it make sense to skip the
+ * preparation on the next requests?
*/
ConditionVariablePrepareToSleep(&shared->cv);
for (;;)
{
- bool valid;
+ int response;
SpinLockAcquire(&shared->mutex);
- valid = shared->sfs_valid;
+ response = shared->response;
SpinLockRelease(&shared->mutex);
- if (valid)
+ if (response & WORKER_RESPONSE_SNAPSHOT)
break;
ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
@@ -3851,7 +4087,9 @@ get_initial_snapshot(DecodingWorker *worker)
ConditionVariableCancelSleep();
/* Read the snapshot from a file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_snapshot,
+ true);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
BufFileReadExact(file, &snap_size, sizeof(snap_size));
snap_space = (char *) palloc(snap_size);
@@ -3859,7 +4097,8 @@ get_initial_snapshot(DecodingWorker *worker)
BufFileClose(file);
SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = false;
+ shared->response &= ~WORKER_RESPONSE_SNAPSHOT;
+ Assert(!shared->snapshot_requested);
SpinLockRelease(&shared->mutex);
/* Restore it. */
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index a956892f42f..c8bc85d8bcc 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -1003,6 +1003,7 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
xl_heap_insert *xlrec;
ReorderBufferChange *change;
RelFileLocator target_locator;
+ BlockNumber blknum;
xlrec = (xl_heap_insert *) XLogRecGetData(r);
@@ -1014,7 +1015,7 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
return;
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1039,6 +1040,15 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
DecodeXLogTuple(tupledata, datalen, change->data.tp.newtuple);
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the corresponding
+ * part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.newtuple->t_self, blknum,
+ xlrec->offnum);
+
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr,
@@ -1060,11 +1070,12 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferChange *change;
char *data;
RelFileLocator target_locator;
+ BlockNumber new_blknum;
xlrec = (xl_heap_update *) XLogRecGetData(r);
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &new_blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1090,12 +1101,27 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferAllocTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.newtuple);
+
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the
+ * corresponding part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.newtuple->t_self,
+ new_blknum, xlrec->new_offnum);
}
if (xlrec->flags & XLH_UPDATE_CONTAINS_OLD)
{
Size datalen;
Size tuplelen;
+ BlockNumber old_blknum;
+
+ if (XLogRecHasBlockRef(r, 1))
+ XLogRecGetBlockTag(r, 1, NULL, NULL, &old_blknum);
+ else
+ XLogRecGetBlockTag(r, 0, NULL, NULL, &old_blknum);
/* caution, remaining data in record is not aligned */
data = XLogRecGetData(r) + SizeOfHeapUpdate;
@@ -1106,6 +1132,11 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferAllocTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.oldtuple);
+ /* See above. */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ ItemPointerSet(&change->data.tp.oldtuple->t_self,
+ old_blknum, xlrec->old_offnum);
+
}
change->data.tp.clear_toast_afterwards = true;
@@ -1126,11 +1157,12 @@ DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
xl_heap_delete *xlrec;
ReorderBufferChange *change;
RelFileLocator target_locator;
+ BlockNumber blknum;
xlrec = (xl_heap_delete *) XLogRecGetData(r);
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1162,6 +1194,15 @@ DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
DecodeXLogTuple((char *) xlrec + SizeOfHeapDelete,
datalen, change->data.tp.oldtuple);
+
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the
+ * corresponding part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.oldtuple->t_self, blknum,
+ xlrec->offnum);
}
change->data.tp.clear_toast_afterwards = true;
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index b3fd7fec392..1e445704a1b 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -1670,14 +1670,17 @@ update_progress_txn_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn,
/*
* Set the required catalog xmin horizon for historic snapshots in the current
- * replication slot.
+ * replication slot if catalog is TRUE, or xmin if catalog is FALSE.
*
* Note that in the most cases, we won't be able to immediately use the xmin
* to increase the xmin horizon: we need to wait till the client has confirmed
- * receiving current_lsn with LogicalConfirmReceivedLocation().
+ * receiving current_lsn with LogicalConfirmReceivedLocation(). However,
+ * catalog=FALSE is only allowed for temporary replication slots, so the
+ * horizon is applied immediately.
*/
void
-LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin)
+LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin,
+ bool catalog)
{
bool updated_xmin = false;
ReplicationSlot *slot;
@@ -1688,6 +1691,27 @@ LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin)
Assert(slot != NULL);
SpinLockAcquire(&slot->mutex);
+ if (!catalog)
+ {
+ /*
+ * The non-catalog horizon can only advance in temporary slots, so
+ * update it in the shared memory immediately (w/o requiring prior
+ * saving to disk).
+ */
+ Assert(slot->data.persistency == RS_TEMPORARY);
+
+ /*
+ * The horizon must not go backwards, however it's o.k. to become
+ * invalid.
+ */
+ Assert(!TransactionIdIsValid(slot->effective_xmin) ||
+ !TransactionIdIsValid(xmin) ||
+ TransactionIdFollowsOrEquals(xmin, slot->effective_xmin));
+
+ slot->effective_xmin = xmin;
+ SpinLockRelease(&slot->mutex);
+ return;
+ }
/*
* don't overwrite if we already have a newer xmin. This can happen if we
diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c
index f18c6fb52b5..273f65d6cc8 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -3734,6 +3734,56 @@ ReorderBufferXidHasCatalogChanges(ReorderBuffer *rb, TransactionId xid)
return rbtxn_has_catalog_changes(txn);
}
+/*
+ * Check if a transaction (or its subtransaction) contains a heap change.
+ */
+bool
+ReorderBufferXidHasHeapChanges(ReorderBuffer *rb, TransactionId xid)
+{
+ ReorderBufferTXN *txn;
+ dlist_iter iter;
+
+ txn = ReorderBufferTXNByXid(rb, xid, false, NULL, InvalidXLogRecPtr,
+ false);
+ if (txn == NULL)
+ return false;
+
+ dlist_foreach(iter, &txn->changes)
+ {
+ ReorderBufferChange *change;
+
+ change = dlist_container(ReorderBufferChange, node, iter.cur);
+
+ switch (change->action)
+ {
+ case REORDER_BUFFER_CHANGE_INSERT:
+ case REORDER_BUFFER_CHANGE_UPDATE:
+ case REORDER_BUFFER_CHANGE_DELETE:
+ return true;
+ default:
+ break;
+ }
+ }
+
+ /* Check subtransactions. */
+
+ /*
+ * TODO Verify that subtransactions must be assigned to the top-level
+ * transactions by now.
+ */
+ dlist_foreach(iter, &txn->subtxns)
+ {
+ ReorderBufferTXN *subtxn;
+
+ subtxn = dlist_container(ReorderBufferTXN, node, iter.cur);
+
+ if (ReorderBufferXidHasHeapChanges(rb, subtxn->xid))
+ return true;
+ }
+
+ return false;
+}
+
/*
* ReorderBufferXidHasBaseSnapshot
* Have we already set the base snapshot for the given txn/subtxn?
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 7643dfe31bb..4bc6cd22496 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -128,6 +128,7 @@
#include "access/heapam_xlog.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "commands/cluster.h"
#include "common/file_utils.h"
#include "miscadmin.h"
#include "pgstat.h"
@@ -496,7 +497,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
* we do not set MyProc->xmin). XXX Do we yet need to add some restrictions?
*/
Snapshot
-SnapBuildInitialSnapshotForRepack(SnapBuild *builder)
+SnapBuildSnapshotForRepack(SnapBuild *builder)
{
Snapshot snap;
@@ -1035,6 +1036,28 @@ SnapBuildCommitTxn(SnapBuild *builder, XLogRecPtr lsn, TransactionId xid,
}
}
+ /*
+ * Is REPACKED (CONCURRENTLY) is being run by this backend?
+ */
+ else if (OidIsValid(repacked_rel_locator.relNumber))
+ {
+ Assert(builder->building_full_snapshot);
+
+ /*
+ * In this special mode, heap changes of other relations should not be
+ * decoded at all - see heap_decode(). Thus if we find a single heap
+ * change in this transaction (or its subtransaction), we know that
+ * this transaction changes the relation being repacked.
+ */
+ if (ReorderBufferXidHasHeapChanges(builder->reorder, xid))
+
+ /*
+ * Record the commit so we can build snapshots for the relation
+ * being repacked.
+ */
+ needs_timetravel = true;
+ }
+
for (nxact = 0; nxact < nsubxacts; nxact++)
{
TransactionId subxid = subxacts[nxact];
@@ -1240,7 +1263,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
xmin = running->oldestRunningXid;
elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
- LogicalIncreaseXminForSlot(lsn, xmin);
+ LogicalIncreaseXminForSlot(lsn, xmin, true);
/*
* Also tell the slot where we can restart decoding from. We don't want to
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index fb9956d392d..be1c3ec9626 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -195,6 +195,8 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len));
/* ... and the tuple itself. */
BufFileWrite(dstate->file, tuple->t_data, tuple->t_len);
+ /* CTID is needed as well, to check block ranges. */
+ BufFileWrite(dstate->file, &tuple->t_self, sizeof(tuple->t_self));
/* Free the flat copy if created above. */
if (flattened)
diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat
index 3b9d8349078..a82d284c44c 100644
--- a/src/backend/utils/misc/guc_parameters.dat
+++ b/src/backend/utils/misc/guc_parameters.dat
@@ -2415,6 +2415,16 @@
boot_val => 'true',
},
+# TODO Tune boot_val, 1024 is probably too low.
+{ name => 'repack_snapshot_after', type => 'int', context => 'PGC_USERSET', group => 'DEVELOPER_OPTIONS',
+ short_desc => 'Number of pages after which REPACK (CONCURRENTLY) builds a new snapshot.',
+ flags => 'GUC_UNIT_BLOCKS | GUC_NOT_IN_SAMPLE',
+ variable => 'repack_blocks_per_snapshot',
+ boot_val => '1024',
+ min => '1',
+ max => 'INT_MAX',
+}
+
{ name => 'reserved_connections', type => 'int', context => 'PGC_POSTMASTER', group => 'CONN_AUTH_SETTINGS',
short_desc => 'Sets the number of connection slots reserved for roles with privileges of pg_use_reserved_connections.',
variable => 'ReservedConnections',
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index f87b558c2c6..07f7cfdd6cc 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -42,6 +42,7 @@
#include "catalog/namespace.h"
#include "catalog/storage.h"
#include "commands/async.h"
+#include "commands/cluster.h"
#include "commands/extension.h"
#include "commands/event_trigger.h"
#include "commands/tablespace.h"
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 321c00682ec..6fe3fc760bc 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -629,12 +629,12 @@ typedef struct TableAmRoutine
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead);
+ double *tups_recently_dead,
+ void *tableam_data);
/*
* React to VACUUM command on the relation. The VACUUM can be triggered by
@@ -1647,8 +1647,6 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator)
* not needed for the relation's AM
* - *xid_cutoff - ditto
* - *multi_cutoff - ditto
- * - snapshot - if != NULL, ignore data changes done by transactions that this
- * (MVCC) snapshot considers still in-progress or in the future.
*
* Output parameters:
* - *xid_cutoff - rel's new relfrozenxid value, may be invalid
@@ -1661,19 +1659,19 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead)
+ double *tups_recently_dead,
+ void *tableam_data)
{
OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex,
use_sort, OldestXmin,
- snapshot,
xid_cutoff, multi_cutoff,
num_tuples, tups_vacuumed,
- tups_recently_dead);
+ tups_recently_dead,
+ tableam_data);
}
/*
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 0ac70ec30d7..2b61dce92dc 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -16,10 +16,12 @@
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
+#include "postmaster/bgworker.h"
#include "replication/logical.h"
#include "storage/buffile.h"
#include "storage/lock.h"
#include "storage/relfilelocator.h"
+#include "storage/shm_mq.h"
#include "utils/relcache.h"
#include "utils/resowner.h"
#include "utils/tuplestore.h"
@@ -47,6 +49,63 @@ typedef struct ClusterParams
extern RelFileLocator repacked_rel_locator;
extern RelFileLocator repacked_rel_toast_locator;
+extern PGDLLIMPORT int repack_blocks_per_snapshot;
+
+/*
+ * Everything we need to call ExecInsertIndexTuples().
+ */
+typedef struct IndexInsertState
+{
+ ResultRelInfo *rri;
+ EState *estate;
+} IndexInsertState;
+
+/*
+ * Backend-local information to control the decoding worker.
+ */
+typedef struct DecodingWorker
+{
+ /* The worker. */
+ BackgroundWorkerHandle *handle;
+
+ /* DecodingWorkerShared is in this segment. */
+ dsm_segment *seg;
+
+ /* Handle of the error queue. */
+ shm_mq_handle *error_mqh;
+} DecodingWorker;
+
+/*
+ * Information needed to handle concurrent data changes.
+ */
+typedef struct ConcurrentChangeContext
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ /*
+ * Background worker performing logical decoding of concurrent data
+ * changes.
+ */
+ DecodingWorker *worker;
+
+ /*
+ * The following is needed to find the existing tuple if the change is
+ * UPDATE or DELETE. 'ident_key' should have all the fields except for
+ * 'sk_argument' initialized.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+ int ident_key_nentries;
+
+ /* Needed to update indexes of rel_dst. */
+ IndexInsertState *iistate;
+
+ /* The first block of the scan used to copy the heap. */
+ BlockNumber first_block;
+ /* List of RepackApplyRange objects. */
+ List *block_ranges;
+} ConcurrentChangeContext;
/*
* Stored as a single byte in the output file.
@@ -102,6 +161,12 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence);
+extern void repack_get_concurrent_changes(struct ConcurrentChangeContext *ctx,
+ XLogRecPtr end_of_wal,
+ BlockNumber range_end,
+ bool request_snapshot,
+ bool done);
+extern Snapshot repack_get_snapshot(struct ConcurrentChangeContext *ctx);
extern void RepackWorkerMain(Datum main_arg);
#endif /* CLUSTER_H */
diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h
index 2e562bee5a9..9924f706f20 100644
--- a/src/include/replication/logical.h
+++ b/src/include/replication/logical.h
@@ -137,7 +137,7 @@ extern bool DecodingContextReady(LogicalDecodingContext *ctx);
extern void FreeDecodingContext(LogicalDecodingContext *ctx);
extern void LogicalIncreaseXminForSlot(XLogRecPtr current_lsn,
- TransactionId xmin);
+ TransactionId xmin, bool catalog);
extern void LogicalIncreaseRestartDecodingForSlot(XLogRecPtr current_lsn,
XLogRecPtr restart_lsn);
extern void LogicalConfirmReceivedLocation(XLogRecPtr lsn);
diff --git a/src/include/replication/reorderbuffer.h b/src/include/replication/reorderbuffer.h
index 3cbe106a3c7..b6b739f29f4 100644
--- a/src/include/replication/reorderbuffer.h
+++ b/src/include/replication/reorderbuffer.h
@@ -763,6 +763,7 @@ extern void ReorderBufferProcessXid(ReorderBuffer *rb, TransactionId xid, XLogRe
extern void ReorderBufferXidSetCatalogChanges(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn);
extern bool ReorderBufferXidHasCatalogChanges(ReorderBuffer *rb, TransactionId xid);
+extern bool ReorderBufferXidHasHeapChanges(ReorderBuffer *rb, TransactionId xid);
extern bool ReorderBufferXidHasBaseSnapshot(ReorderBuffer *rb, TransactionId xid);
extern bool ReorderBufferRememberPrepareInfo(ReorderBuffer *rb, TransactionId xid,
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 802fc4b0823..d1f9037fcfb 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,7 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
extern void SnapBuildSnapDecRefcount(Snapshot snap);
extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
-extern Snapshot SnapBuildInitialSnapshotForRepack(SnapBuild *builder);
+extern Snapshot SnapBuildSnapshotForRepack(SnapBuild *builder);
extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
extern void SnapBuildClearExportedSnapshot(void);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 35344910f65..54115135732 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -411,7 +411,6 @@ CatCacheHeader
CatalogId
CatalogIdMapEntry
CatalogIndexState
-ChangeDest
ChangeVarNodes_callback
ChangeVarNodes_context
CheckPoint
@@ -488,6 +487,7 @@ CompressFileHandle
CompressionLocation
CompressorState
ComputeXidHorizonsResult
+ConcurrentChangeContext
ConcurrentChangeKind
ConditionVariable
ConditionVariableMinimallyPadded
@@ -2563,6 +2563,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepOriginId
+RepackApplyRange
RepackCommand
RepackDecodingState
RepackStmt
--
2.47.3
Attachments:
[text/x-diff] v28-0001-Add-REPACK-command.patch (144.9K, ../210036.1765651719@localhost/2-v28-0001-Add-REPACK-command.patch)
download | inline diff:
From 46da847ee07d471134badc362add95ed321269b1 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:17 +0100
Subject: [PATCH 1/6] Add REPACK command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
REPACK absorbs the functionality of VACUUM FULL and CLUSTER in a single
command. Because this functionality is completely different from
regular VACUUM, having it separate from VACUUM makes it easier for users
to understand; as for CLUSTER, the term is heavily overloaded in the
IT world and even in Postgres itself, so it's good that we can avoid it.
This also adds pg_repackdb, a new utility that can invoke the new
commands. This is heavily based on vacuumdb.
Author: Antonin Houska <ah@cybertec.at>
Co-authored-by: Álvaro Herrera <alvherre@kurilemu.de>
Reviewed-by: Mihail Nikalayeu <mihailnikalayeu@gmail.com>
Reviewed-by: Robert Treat <rob@xzilla.net>
Reviewed-by: Euler Taveira <euler@eulerto.com>
Reviewed-by: Matheus Alcantara <matheusssilv97@gmail.com>
Reviewed-by: Junwang Zhao <zhjwpku@gmail.com>
Reviewed-by: jian he <jian.universality@gmail.com>
Discussion: https://postgr.es/m/82651.1720540558@antos
Discussion: https://postgr.es/m/202507262156.sb455angijk6@alvherre.pgsql
---
doc/src/sgml/monitoring.sgml | 223 +++++-
doc/src/sgml/ref/allfiles.sgml | 2 +
doc/src/sgml/ref/cluster.sgml | 97 +--
doc/src/sgml/ref/clusterdb.sgml | 5 +
doc/src/sgml/ref/pg_repackdb.sgml | 488 +++++++++++++
doc/src/sgml/ref/repack.sgml | 328 +++++++++
doc/src/sgml/ref/vacuum.sgml | 33 +-
doc/src/sgml/reference.sgml | 2 +
src/backend/access/heap/heapam_handler.c | 32 +-
src/backend/catalog/index.c | 2 +-
src/backend/catalog/system_views.sql | 29 +-
src/backend/commands/cluster.c | 849 +++++++++++++++--------
src/backend/commands/vacuum.c | 6 +-
src/backend/parser/gram.y | 86 ++-
src/backend/tcop/utility.c | 23 +-
src/backend/utils/adt/pgstatfuncs.c | 2 +
src/bin/psql/tab-complete.in.c | 42 +-
src/bin/scripts/Makefile | 4 +-
src/bin/scripts/meson.build | 2 +
src/bin/scripts/pg_repackdb.c | 240 +++++++
src/bin/scripts/t/103_repackdb.pl | 47 ++
src/bin/scripts/vacuuming.c | 102 ++-
src/bin/scripts/vacuuming.h | 3 +
src/include/commands/cluster.h | 8 +-
src/include/commands/progress.h | 50 +-
src/include/nodes/parsenodes.h | 35 +-
src/include/parser/kwlist.h | 1 +
src/include/tcop/cmdtaglist.h | 1 +
src/include/utils/backend_progress.h | 1 +
src/test/regress/expected/cluster.out | 134 +++-
src/test/regress/expected/rules.out | 72 +-
src/test/regress/sql/cluster.sql | 70 +-
src/tools/pgindent/typedefs.list | 2 +
33 files changed, 2484 insertions(+), 537 deletions(-)
create mode 100644 doc/src/sgml/ref/pg_repackdb.sgml
create mode 100644 doc/src/sgml/ref/repack.sgml
create mode 100644 src/bin/scripts/pg_repackdb.c
create mode 100644 src/bin/scripts/t/103_repackdb.pl
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 817fd9f4ca7..b07fe3294cd 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -405,6 +405,14 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser
</entry>
</row>
+ <row>
+ <entry><structname>pg_stat_progress_repack</structname><indexterm><primary>pg_stat_progress_repack</primary></indexterm></entry>
+ <entry>One row for each backend running
+ <command>REPACK</command>, showing current progress. See
+ <xref linkend="repack-progress-reporting"/>.
+ </entry>
+ </row>
+
<row>
<entry><structname>pg_stat_progress_basebackup</structname><indexterm><primary>pg_stat_progress_basebackup</primary></indexterm></entry>
<entry>One row for each WAL sender process streaming a base backup,
@@ -5609,7 +5617,8 @@ FROM pg_stat_get_backend_idset() AS backendid;
certain commands during command execution. Currently, the only commands
which support progress reporting are <command>ANALYZE</command>,
<command>CLUSTER</command>,
- <command>CREATE INDEX</command>, <command>VACUUM</command>,
+ <command>CREATE INDEX</command>, <command>REPACK</command>,
+ <command>VACUUM</command>,
<command>COPY</command>,
and <xref linkend="protocol-replication-base-backup"/> (i.e., replication
command that <xref linkend="app-pgbasebackup"/> issues to take
@@ -6093,6 +6102,218 @@ FROM pg_stat_get_backend_idset() AS backendid;
</table>
</sect2>
+ <sect2 id="repack-progress-reporting">
+ <title>REPACK Progress Reporting</title>
+
+ <indexterm>
+ <primary>pg_stat_progress_repack</primary>
+ </indexterm>
+
+ <para>
+ Whenever <command>REPACK</command> is running,
+ the <structname>pg_stat_progress_repack</structname> view will contain a
+ row for each backend that is currently running the command. The tables
+ below describe the information that will be reported and provide
+ information about how to interpret it.
+ </para>
+
+ <table id="pg-stat-progress-repack-view" xreflabel="pg_stat_progress_repack">
+ <title><structname>pg_stat_progress_repack</structname> View</title>
+ <tgroup cols="1">
+ <thead>
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ Column Type
+ </para>
+ <para>
+ Description
+ </para></entry>
+ </row>
+ </thead>
+
+ <tbody>
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>pid</structfield> <type>integer</type>
+ </para>
+ <para>
+ Process ID of backend.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>datid</structfield> <type>oid</type>
+ </para>
+ <para>
+ OID of the database to which this backend is connected.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>datname</structfield> <type>name</type>
+ </para>
+ <para>
+ Name of the database to which this backend is connected.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>relid</structfield> <type>oid</type>
+ </para>
+ <para>
+ OID of the table being repacked.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>phase</structfield> <type>text</type>
+ </para>
+ <para>
+ Current processing phase. See <xref linkend="repack-phases"/>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>repack_index_relid</structfield> <type>oid</type>
+ </para>
+ <para>
+ If the table is being scanned using an index, this is the OID of the
+ index being used; otherwise, it is zero.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_scanned</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples scanned.
+ This counter only advances when the phase is
+ <literal>seq scanning heap</literal>,
+ <literal>index scanning heap</literal>
+ or <literal>writing new heap</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_written</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples written.
+ This counter only advances when the phase is
+ <literal>seq scanning heap</literal>,
+ <literal>index scanning heap</literal>
+ or <literal>writing new heap</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_blks_total</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Total number of heap blocks in the table. This number is reported
+ as of the beginning of <literal>seq scanning heap</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_blks_scanned</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap blocks scanned. This counter only advances when the
+ phase is <literal>seq scanning heap</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>index_rebuild_count</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of indexes rebuilt. This counter only advances when the phase
+ is <literal>rebuilding index</literal>.
+ </para></entry>
+ </row>
+ </tbody>
+ </tgroup>
+ </table>
+
+ <table id="repack-phases">
+ <title>REPACK Phases</title>
+ <tgroup cols="2">
+ <colspec colname="col1" colwidth="1*"/>
+ <colspec colname="col2" colwidth="2*"/>
+ <thead>
+ <row>
+ <entry>Phase</entry>
+ <entry>Description</entry>
+ </row>
+ </thead>
+
+ <tbody>
+ <row>
+ <entry><literal>initializing</literal></entry>
+ <entry>
+ The command is preparing to begin scanning the heap. This phase is
+ expected to be very brief.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>seq scanning heap</literal></entry>
+ <entry>
+ The command is currently scanning the table using a sequential scan.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>index scanning heap</literal></entry>
+ <entry>
+ <command>REPACK</command> is currently scanning the table using an index scan.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>sorting tuples</literal></entry>
+ <entry>
+ <command>REPACK</command> is currently sorting tuples.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>writing new heap</literal></entry>
+ <entry>
+ <command>REPACK</command> is currently writing the new heap.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>swapping relation files</literal></entry>
+ <entry>
+ The command is currently swapping newly-built files into place.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>rebuilding index</literal></entry>
+ <entry>
+ The command is currently rebuilding an index.
+ </entry>
+ </row>
+ <row>
+ <entry><literal>performing final cleanup</literal></entry>
+ <entry>
+ The command is performing final cleanup. When this phase is
+ completed, <command>REPACK</command> will end.
+ </entry>
+ </row>
+ </tbody>
+ </tgroup>
+ </table>
+ </sect2>
+
<sect2 id="copy-progress-reporting">
<title>COPY Progress Reporting</title>
diff --git a/doc/src/sgml/ref/allfiles.sgml b/doc/src/sgml/ref/allfiles.sgml
index e167406c744..5df944d13ca 100644
--- a/doc/src/sgml/ref/allfiles.sgml
+++ b/doc/src/sgml/ref/allfiles.sgml
@@ -167,6 +167,7 @@ Complete list of usable sgml source files in this directory.
<!ENTITY refreshMaterializedView SYSTEM "refresh_materialized_view.sgml">
<!ENTITY reindex SYSTEM "reindex.sgml">
<!ENTITY releaseSavepoint SYSTEM "release_savepoint.sgml">
+<!ENTITY repack SYSTEM "repack.sgml">
<!ENTITY reset SYSTEM "reset.sgml">
<!ENTITY revoke SYSTEM "revoke.sgml">
<!ENTITY rollback SYSTEM "rollback.sgml">
@@ -213,6 +214,7 @@ Complete list of usable sgml source files in this directory.
<!ENTITY pgIsready SYSTEM "pg_isready.sgml">
<!ENTITY pgReceivewal SYSTEM "pg_receivewal.sgml">
<!ENTITY pgRecvlogical SYSTEM "pg_recvlogical.sgml">
+<!ENTITY pgRepackdb SYSTEM "pg_repackdb.sgml">
<!ENTITY pgResetwal SYSTEM "pg_resetwal.sgml">
<!ENTITY pgRestore SYSTEM "pg_restore.sgml">
<!ENTITY pgRewind SYSTEM "pg_rewind.sgml">
diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0b47460080b..2cda711bc9f 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -33,51 +33,13 @@ CLUSTER [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <r
<title>Description</title>
<para>
- <command>CLUSTER</command> instructs <productname>PostgreSQL</productname>
- to cluster the table specified
- by <replaceable class="parameter">table_name</replaceable>
- based on the index specified by
- <replaceable class="parameter">index_name</replaceable>. The index must
- already have been defined on
- <replaceable class="parameter">table_name</replaceable>.
+ The <command>CLUSTER</command> command is equivalent to
+ <xref linkend="sql-repack"/> with an <literal>USING INDEX</literal>
+ clause. See there for more details.
</para>
- <para>
- When a table is clustered, it is physically reordered
- based on the index information. Clustering is a one-time operation:
- when the table is subsequently updated, the changes are
- not clustered. That is, no attempt is made to store new or
- updated rows according to their index order. (If one wishes, one can
- periodically recluster by issuing the command again. Also, setting
- the table's <literal>fillfactor</literal> storage parameter to less than
- 100% can aid in preserving cluster ordering during updates, since updated
- rows are kept on the same page if enough space is available there.)
- </para>
-
- <para>
- When a table is clustered, <productname>PostgreSQL</productname>
- remembers which index it was clustered by. The form
- <command>CLUSTER <replaceable class="parameter">table_name</replaceable></command>
- reclusters the table using the same index as before. You can also
- use the <literal>CLUSTER</literal> or <literal>SET WITHOUT CLUSTER</literal>
- forms of <link linkend="sql-altertable"><command>ALTER TABLE</command></link> to set the index to be used for
- future cluster operations, or to clear any previous setting.
- </para>
-
- <para>
- <command>CLUSTER</command> without a
- <replaceable class="parameter">table_name</replaceable> reclusters all the
- previously-clustered tables in the current database that the calling user
- has privileges for. This form of <command>CLUSTER</command> cannot be
- executed inside a transaction block.
- </para>
+<!-- Do we need to describe exactly which options map to what? They seem obvious to me. -->
- <para>
- When a table is being clustered, an <literal>ACCESS
- EXCLUSIVE</literal> lock is acquired on it. This prevents any other
- database operations (both reads and writes) from operating on the
- table until the <command>CLUSTER</command> is finished.
- </para>
</refsect1>
<refsect1>
@@ -136,63 +98,12 @@ CLUSTER [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <r
on the table.
</para>
- <para>
- In cases where you are accessing single rows randomly
- within a table, the actual order of the data in the
- table is unimportant. However, if you tend to access some
- data more than others, and there is an index that groups
- them together, you will benefit from using <command>CLUSTER</command>.
- If you are requesting a range of indexed values from a table, or a
- single indexed value that has multiple rows that match,
- <command>CLUSTER</command> will help because once the index identifies the
- table page for the first row that matches, all other rows
- that match are probably already on the same table page,
- and so you save disk accesses and speed up the query.
- </para>
-
- <para>
- <command>CLUSTER</command> can re-sort the table using either an index scan
- on the specified index, or (if the index is a b-tree) a sequential
- scan followed by sorting. It will attempt to choose the method that
- will be faster, based on planner cost parameters and available statistical
- information.
- </para>
-
<para>
While <command>CLUSTER</command> is running, the <xref
linkend="guc-search-path"/> is temporarily changed to <literal>pg_catalog,
pg_temp</literal>.
</para>
- <para>
- When an index scan is used, a temporary copy of the table is created that
- contains the table data in the index order. Temporary copies of each
- index on the table are created as well. Therefore, you need free space on
- disk at least equal to the sum of the table size and the index sizes.
- </para>
-
- <para>
- When a sequential scan and sort is used, a temporary sort file is
- also created, so that the peak temporary space requirement is as much
- as double the table size, plus the index sizes. This method is often
- faster than the index scan method, but if the disk space requirement is
- intolerable, you can disable this choice by temporarily setting <xref
- linkend="guc-enable-sort"/> to <literal>off</literal>.
- </para>
-
- <para>
- It is advisable to set <xref linkend="guc-maintenance-work-mem"/> to
- a reasonably large value (but not more than the amount of RAM you can
- dedicate to the <command>CLUSTER</command> operation) before clustering.
- </para>
-
- <para>
- Because the planner records statistics about the ordering of
- tables, it is advisable to run <link linkend="sql-analyze"><command>ANALYZE</command></link>
- on the newly clustered table.
- Otherwise, the planner might make poor choices of query plans.
- </para>
-
<para>
Because <command>CLUSTER</command> remembers which indexes are clustered,
one can cluster the tables one wants clustered manually the first time,
diff --git a/doc/src/sgml/ref/clusterdb.sgml b/doc/src/sgml/ref/clusterdb.sgml
index 0d2051bf6f1..b50c9581a98 100644
--- a/doc/src/sgml/ref/clusterdb.sgml
+++ b/doc/src/sgml/ref/clusterdb.sgml
@@ -64,6 +64,11 @@ PostgreSQL documentation
this utility and via other methods for accessing the server.
</para>
+ <para>
+ <application>clusterdb</application> has been superseded by
+ <application>pg_repackdb</application>.
+ </para>
+
</refsect1>
diff --git a/doc/src/sgml/ref/pg_repackdb.sgml b/doc/src/sgml/ref/pg_repackdb.sgml
new file mode 100644
index 00000000000..b313b54ab63
--- /dev/null
+++ b/doc/src/sgml/ref/pg_repackdb.sgml
@@ -0,0 +1,488 @@
+<!--
+doc/src/sgml/ref/pg_repackdb.sgml
+PostgreSQL documentation
+-->
+
+<refentry id="app-pgrepackdb">
+ <indexterm zone="app-pgrepackdb">
+ <primary>pg_repackdb</primary>
+ </indexterm>
+
+ <refmeta>
+ <refentrytitle><application>pg_repackdb</application></refentrytitle>
+ <manvolnum>1</manvolnum>
+ <refmiscinfo>Application</refmiscinfo>
+ </refmeta>
+
+ <refnamediv>
+ <refname>pg_repackdb</refname>
+ <refpurpose>repack and analyze a <productname>PostgreSQL</productname>
+ database</refpurpose>
+ </refnamediv>
+
+ <refsynopsisdiv>
+ <cmdsynopsis>
+ <command>pg_repackdb</command>
+ <arg rep="repeat"><replaceable>connection-option</replaceable></arg>
+ <arg rep="repeat"><replaceable>option</replaceable></arg>
+
+ <arg choice="plain" rep="repeat">
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><option>-t</option></arg>
+ <arg choice="plain"><option>--table</option></arg>
+ </group>
+ <replaceable>table</replaceable>
+ <arg choice="opt">( <replaceable class="parameter">column</replaceable> [,...] )</arg>
+ </arg>
+ </arg>
+
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><replaceable>dbname</replaceable></arg>
+ <arg choice="plain"><option>-a</option></arg>
+ <arg choice="plain"><option>--all</option></arg>
+ </group>
+ </arg>
+ </cmdsynopsis>
+
+ <cmdsynopsis>
+ <command>pg_repackdb</command>
+ <arg rep="repeat"><replaceable>connection-option</replaceable></arg>
+ <arg rep="repeat"><replaceable>option</replaceable></arg>
+
+ <arg choice="plain" rep="repeat">
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><option>-n</option></arg>
+ <arg choice="plain"><option>--schema</option></arg>
+ </group>
+ <replaceable>schema</replaceable>
+ </arg>
+ </arg>
+
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><replaceable>dbname</replaceable></arg>
+ <arg choice="plain"><option>-a</option></arg>
+ <arg choice="plain"><option>--all</option></arg>
+ </group>
+ </arg>
+ </cmdsynopsis>
+
+ <cmdsynopsis>
+ <command>pg_repackdb</command>
+ <arg rep="repeat"><replaceable>connection-option</replaceable></arg>
+ <arg rep="repeat"><replaceable>option</replaceable></arg>
+
+ <arg choice="plain" rep="repeat">
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><option>-N</option></arg>
+ <arg choice="plain"><option>--exclude-schema</option></arg>
+ </group>
+ <replaceable>schema</replaceable>
+ </arg>
+ </arg>
+
+ <arg choice="opt">
+ <group choice="plain">
+ <arg choice="plain"><replaceable>dbname</replaceable></arg>
+ <arg choice="plain"><option>-a</option></arg>
+ <arg choice="plain"><option>--all</option></arg>
+ </group>
+ </arg>
+ </cmdsynopsis>
+ </refsynopsisdiv>
+
+ <refsect1>
+ <title>Description</title>
+
+ <para>
+ <application>pg_repackdb</application> is a utility for repacking a
+ <productname>PostgreSQL</productname> database.
+ <application>pg_repackdb</application> will also generate internal
+ statistics used by the <productname>PostgreSQL</productname> query
+ optimizer.
+ </para>
+
+ <para>
+ <application>pg_repackdb</application> is a wrapper around the SQL
+ command <link linkend="sql-repack"><command>REPACK</command></link> There
+ is no effective difference between repacking and analyzing databases via
+ this utility and via other methods for accessing the server.
+ </para>
+ </refsect1>
+
+ <refsect1>
+ <title>Options</title>
+
+ <para>
+ <application>pg_repackdb</application> accepts the following command-line arguments:
+ <variablelist>
+ <varlistentry>
+ <term><option>-a</option></term>
+ <term><option>--all</option></term>
+ <listitem>
+ <para>
+ Repack all databases.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option><optional>-d</optional> <replaceable class="parameter">dbname</replaceable></option></term>
+ <term><option><optional>--dbname=</optional><replaceable class="parameter">dbname</replaceable></option></term>
+ <listitem>
+ <para>
+ Specifies the name of the database to be repacked or analyzed,
+ when <option>-a</option>/<option>--all</option> is not used. If this
+ is not specified, the database name is read from the environment
+ variable <envar>PGDATABASE</envar>. If that is not set, the user name
+ specified for the connection is used.
+ The <replaceable>dbname</replaceable> can be
+ a <link linkend="libpq-connstring">connection string</link>. If so,
+ connection string parameters will override any conflicting command
+ line options.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-e</option></term>
+ <term><option>--echo</option></term>
+ <listitem>
+ <para>
+ Echo the commands that <application>pg_repackdb</application>
+ generates and sends to the server.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--index<optional>=<replaceable class="parameter">index_name</replaceable></optional></option></term>
+ <listitem>
+ <para>
+ Pass the <literal>USING INDEX</literal> clause to <literal>REPACK</literal>,
+ and optionally the index name to specify.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-j <replaceable class="parameter">njobs</replaceable></option></term>
+ <term><option>--jobs=<replaceable class="parameter">njobs</replaceable></option></term>
+ <listitem>
+ <para>
+ Execute the repack or analyze commands in parallel by running
+ <replaceable class="parameter">njobs</replaceable>
+ commands simultaneously. This option may reduce the processing time
+ but it also increases the load on the database server.
+ </para>
+ <para>
+ <application>pg_repackdb</application> will open
+ <replaceable class="parameter">njobs</replaceable> connections to the
+ database, so make sure your <xref linkend="guc-max-connections"/>
+ setting is high enough to accommodate all connections.
+ </para>
+ <para>
+ Note that using this mode might cause deadlock failures if certain
+ system catalogs are processed in parallel.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-n <replaceable class="parameter">schema</replaceable></option></term>
+ <term><option>--schema=<replaceable class="parameter">schema</replaceable></option></term>
+ <listitem>
+ <para>
+ Repack or analyze all tables in
+ <replaceable class="parameter">schema</replaceable> only. Multiple
+ schemas can be repacked by writing multiple <option>-n</option>
+ switches.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-N <replaceable class="parameter">schema</replaceable></option></term>
+ <term><option>--exclude-schema=<replaceable class="parameter">schema</replaceable></option></term>
+ <listitem>
+ <para>
+ Do not repack or analyze any tables in
+ <replaceable class="parameter">schema</replaceable>. Multiple schemas
+ can be excluded by writing multiple <option>-N</option> switches.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-q</option></term>
+ <term><option>--quiet</option></term>
+ <listitem>
+ <para>
+ Do not display progress messages.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-t <replaceable class="parameter">table</replaceable> [ (<replaceable class="parameter">column</replaceable> [,...]) ]</option></term>
+ <term><option>--table=<replaceable class="parameter">table</replaceable> [ (<replaceable class="parameter">column</replaceable> [,...]) ]</option></term>
+ <listitem>
+ <para>
+ Repack or analyze <replaceable class="parameter">table</replaceable>
+ only. Column names can be specified only in conjunction with
+ the <option>--analyze</option> option. Multiple tables can be
+ repacked by writing multiple
+ <option>-t</option> switches.
+ </para>
+ <tip>
+ <para>
+ If you specify columns, you probably have to escape the parentheses
+ from the shell. (See examples below.)
+ </para>
+ </tip>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-v</option></term>
+ <term><option>--verbose</option></term>
+ <listitem>
+ <para>
+ Print detailed information during processing.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-V</option></term>
+ <term><option>--version</option></term>
+ <listitem>
+ <para>
+ Print the <application>pg_repackdb</application> version and exit.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-z</option></term>
+ <term><option>--analyze</option></term>
+ <listitem>
+ <para>
+ Also calculate statistics for use by the optimizer. If a column name
+ list is given, only compute statistics for those columns.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-?</option></term>
+ <term><option>--help</option></term>
+ <listitem>
+ <para>
+ Show help about <application>pg_repackdb</application> command line
+ arguments, and exit.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
+ </para>
+
+ <para>
+ <application>pg_repackdb</application> also accepts
+ the following command-line arguments for connection parameters:
+ <variablelist>
+ <varlistentry>
+ <term><option>-h <replaceable class="parameter">host</replaceable></option></term>
+ <term><option>--host=<replaceable class="parameter">host</replaceable></option></term>
+ <listitem>
+ <para>
+ Specifies the host name of the machine on which the server
+ is running. If the value begins with a slash, it is used
+ as the directory for the Unix domain socket.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-p <replaceable class="parameter">port</replaceable></option></term>
+ <term><option>--port=<replaceable class="parameter">port</replaceable></option></term>
+ <listitem>
+ <para>
+ Specifies the TCP port or local Unix domain socket file
+ extension on which the server
+ is listening for connections.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-U <replaceable class="parameter">username</replaceable></option></term>
+ <term><option>--username=<replaceable class="parameter">username</replaceable></option></term>
+ <listitem>
+ <para>
+ User name to connect as.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-w</option></term>
+ <term><option>--no-password</option></term>
+ <listitem>
+ <para>
+ Never issue a password prompt. If the server requires
+ password authentication and a password is not available by
+ other means such as a <filename>.pgpass</filename> file, the
+ connection attempt will fail. This option can be useful in
+ batch jobs and scripts where no user is present to enter a
+ password.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-W</option></term>
+ <term><option>--password</option></term>
+ <listitem>
+ <para>
+ Force <application>pg_repackdb</application> to prompt for a
+ password before connecting to a database.
+ </para>
+
+ <para>
+ This option is never essential, since
+ <application>pg_repackdb</application> will automatically prompt
+ for a password if the server demands password authentication.
+ However, <application>pg_repackdb</application> will waste a
+ connection attempt finding out that the server wants a password.
+ In some cases it is worth typing <option>-W</option> to avoid the extra
+ connection attempt.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--maintenance-db=<replaceable class="parameter">dbname</replaceable></option></term>
+ <listitem>
+ <para>
+ When the <option>-a</option>/<option>--all</option> is used, connect
+ to this database to gather the list of databases to repack.
+ If not specified, the <literal>postgres</literal> database will be used,
+ or if that does not exist, <literal>template1</literal> will be used.
+ This can be a <link linkend="libpq-connstring">connection
+ string</link>. If so, connection string parameters will override any
+ conflicting command line options. Also, connection string parameters
+ other than the database name itself will be re-used when connecting
+ to other databases.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect1>
+
+
+ <refsect1>
+ <title>Environment</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><envar>PGDATABASE</envar></term>
+ <term><envar>PGHOST</envar></term>
+ <term><envar>PGPORT</envar></term>
+ <term><envar>PGUSER</envar></term>
+
+ <listitem>
+ <para>
+ Default connection parameters
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><envar>PG_COLOR</envar></term>
+ <listitem>
+ <para>
+ Specifies whether to use color in diagnostic messages. Possible values
+ are <literal>always</literal>, <literal>auto</literal> and
+ <literal>never</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+
+ <para>
+ This utility, like most other <productname>PostgreSQL</productname> utilities,
+ also uses the environment variables supported by <application>libpq</application>
+ (see <xref linkend="libpq-envars"/>).
+ </para>
+
+ </refsect1>
+
+
+ <refsect1>
+ <title>Diagnostics</title>
+
+ <para>
+ In case of difficulty, see
+ <xref linkend="sql-repack"/> and <xref linkend="app-psql"/> for
+ discussions of potential problems and error messages.
+ The database server must be running at the
+ targeted host. Also, any default connection settings and environment
+ variables used by the <application>libpq</application> front-end
+ library will apply.
+ </para>
+
+ </refsect1>
+
+ <refsect1>
+ <title>Examples</title>
+
+ <para>
+ To repack the database <literal>test</literal>:
+<screen>
+<prompt>$ </prompt><userinput>pg_repackdb test</userinput>
+</screen>
+ </para>
+
+ <para>
+ To repack and analyze for the optimizer a database named
+ <literal>bigdb</literal>:
+<screen>
+<prompt>$ </prompt><userinput>pg_repackdb --analyze bigdb</userinput>
+</screen>
+ </para>
+
+ <para>
+ To repack a single table
+ <literal>foo</literal> in a database named
+ <literal>xyzzy</literal>, and analyze a single column
+ <literal>bar</literal> of the table for the optimizer:
+<screen>
+<prompt>$ </prompt><userinput>pg_repackdb --analyze --verbose --table='foo(bar)' xyzzy</userinput>
+</screen></para>
+
+ <para>
+ To repack all tables in the <literal>foo</literal> and <literal>bar</literal> schemas
+ in a database named <literal>xyzzy</literal>:
+<screen>
+<prompt>$ </prompt><userinput>pg_repackdb --schema='foo' --schema='bar' xyzzy</userinput>
+</screen></para>
+
+
+ </refsect1>
+
+ <refsect1>
+ <title>See Also</title>
+
+ <simplelist type="inline">
+ <member><xref linkend="sql-repack"/></member>
+ </simplelist>
+ </refsect1>
+
+</refentry>
diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml
new file mode 100644
index 00000000000..61d5c2cdef1
--- /dev/null
+++ b/doc/src/sgml/ref/repack.sgml
@@ -0,0 +1,328 @@
+<!--
+doc/src/sgml/ref/repack.sgml
+PostgreSQL documentation
+-->
+
+<refentry id="sql-repack">
+ <indexterm zone="sql-repack">
+ <primary>REPACK</primary>
+ </indexterm>
+
+ <refmeta>
+ <refentrytitle>REPACK</refentrytitle>
+ <manvolnum>7</manvolnum>
+ <refmiscinfo>SQL - Language Statements</refmiscinfo>
+ </refmeta>
+
+ <refnamediv>
+ <refname>REPACK</refname>
+ <refpurpose>rewrite a table to reclaim disk space</refpurpose>
+ </refnamediv>
+
+ <refsynopsisdiv>
+<synopsis>
+REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <replaceable class="parameter">table_and_columns</replaceable> [ USING INDEX [ <replaceable class="parameter">index_name</replaceable> ] ] ]
+REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING INDEX
+
+<phrase>where <replaceable class="parameter">option</replaceable> can be one of:</phrase>
+
+ VERBOSE [ <replaceable class="parameter">boolean</replaceable> ]
+ ANALYZE [ <replaceable class="parameter">boolean</replaceable> ]
+
+<phrase>and <replaceable class="parameter">table_and_columns</replaceable> is:</phrase>
+
+ <replaceable class="parameter">table_name</replaceable> [ ( <replaceable class="parameter">column_name</replaceable> [, ...] ) ]
+</synopsis>
+ </refsynopsisdiv>
+
+ <refsect1>
+ <title>Description</title>
+
+ <para>
+ <command>REPACK</command> reclaims storage occupied by dead
+ tuples. Unlike <command>VACUUM</command>, it does so by rewriting the
+ entire contents of the table specified
+ by <replaceable class="parameter">table_name</replaceable> into a new disk
+ file with no extra space (except for the space guaranteed by
+ the <literal>fillfactor</literal> storage parameter), allowing unused space
+ to be returned to the operating system.
+ </para>
+
+ <para>
+ Without
+ a <replaceable class="parameter">table_name</replaceable>, <command>REPACK</command>
+ processes every table and materialized view in the current database that
+ the current user has the <literal>MAINTAIN</literal> privilege on. This
+ form of <command>REPACK</command> cannot be executed inside a transaction
+ block.
+ </para>
+
+ <para>
+ If a <literal>USING INDEX</literal> clause is specified, the rows are
+ physically reordered based on information from an index. Please see the
+ notes on clustering below.
+ </para>
+
+ <para>
+ When a table is being repacked, an <literal>ACCESS EXCLUSIVE</literal> lock
+ is acquired on it. This prevents any other database operations (both reads
+ and writes) from operating on the table until the <command>REPACK</command>
+ is finished.
+ </para>
+
+ <refsect2 id="sql-repack-notes-on-clustering" xreflabel="Notes on Clustering">
+ <title>Notes on Clustering</title>
+
+ <para>
+ If the <literal>USING INDEX</literal> clause is specified, the rows in
+ the table are physically reordered following an index: if an index name
+ is specified in the command, then that index is used; if no index name
+ is specified, then the index that has been configured as the index to
+ cluster on. If no index has been configured in this way, an error is
+ thrown. The index given in the <literal>USING INDEX</literal> clause
+ is configured as the index to cluster on, as well as an index given
+ to the <command>CLUSTER</command> command. An index can be set
+ manually using <command>ALTER TABLE ... CLUSTER ON</command>, and reset
+ with <command>ALTER TABLE ... SET WITHOUT CLUSTER</command>.
+ </para>
+
+ <para>
+ If no table name is specified in <command>REPACK USING INDEX</command>,
+ all tables which have a clustering index defined and which the calling
+ user has privileges for are processed.
+ </para>
+
+ <para>
+ Clustering is a one-time operation: when the table is
+ subsequently updated, the changes are not clustered. That is, no attempt
+ is made to store new or updated rows according to their index order. (If
+ one wishes, one can periodically recluster by issuing the command again.
+ Also, setting the table's <literal>fillfactor</literal> storage parameter
+ to less than 100% can aid in preserving cluster ordering during updates,
+ since updated rows are kept on the same page if enough space is available
+ there.)
+ </para>
+
+ <para>
+ In cases where you are accessing single rows randomly within a table, the
+ actual order of the data in the table is unimportant. However, if you tend
+ to access some data more than others, and there is an index that groups
+ them together, you will benefit from using clustering. If
+ you are requesting a range of indexed values from a table, or a single
+ indexed value that has multiple rows that match,
+ <command>REPACK</command> will help because once the index identifies the
+ table page for the first row that matches, all other rows that match are
+ probably already on the same table page, and so you save disk accesses and
+ speed up the query.
+ </para>
+
+ <para>
+ <command>REPACK</command> can re-sort the table using either an index scan
+ on the specified index (if the index is a b-tree), or a sequential scan
+ followed by sorting. It will attempt to choose the method that will be
+ faster, based on planner cost parameters and available statistical
+ information.
+ </para>
+
+ <para>
+ Because the planner records statistics about the ordering of tables, it is
+ advisable to
+ run <link linkend="sql-analyze"><command>ANALYZE</command></link> on the
+ newly repacked table. Otherwise, the planner might make poor choices of
+ query plans.
+ </para>
+ </refsect2>
+
+ <refsect2 id="sql-repack-notes-on-resources" xreflabel="Notes on Resources">
+ <title>Notes on Resources</title>
+
+ <para>
+ When an index scan or a sequential scan without sort is used, a temporary
+ copy of the table is created that contains the table data in the index
+ order. Temporary copies of each index on the table are created as well.
+ Therefore, you need free space on disk at least equal to the sum of the
+ table size and the index sizes.
+ </para>
+
+ <para>
+ When a sequential scan and sort is used, a temporary sort file is also
+ created, so that the peak temporary space requirement is as much as double
+ the table size, plus the index sizes. This method is often faster than
+ the index scan method, but if the disk space requirement is intolerable,
+ you can disable this choice by temporarily setting
+ <xref linkend="guc-enable-sort"/> to <literal>off</literal>.
+ </para>
+
+ <para>
+ It is advisable to set <xref linkend="guc-maintenance-work-mem"/> to a
+ reasonably large value (but not more than the amount of RAM you can
+ dedicate to the <command>REPACK</command> operation) before repacking.
+ </para>
+ </refsect2>
+
+ </refsect1>
+
+ <refsect1>
+ <title>Parameters</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><replaceable class="parameter">table_name</replaceable></term>
+ <listitem>
+ <para>
+ The name (possibly schema-qualified) of a table.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><replaceable class="parameter">column_name</replaceable></term>
+ <listitem>
+ <para>
+ The name of a specific column to analyze. Defaults to all columns.
+ If a column list is specific, <literal>ANALYZE</literal> must also
+ be specified.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><replaceable class="parameter">index_name</replaceable></term>
+ <listitem>
+ <para>
+ The name of an index.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><literal>VERBOSE</literal></term>
+ <listitem>
+ <para>
+ Prints a progress report as each table is repacked
+ at <literal>INFO</literal> level.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><literal>ANALYZE</literal></term>
+ <term><literal>ANALYSE</literal></term>
+ <listitem>
+ <para>
+ Applies <xref linkend="sql-analyze"/> on the table after repacking. This is
+ currently only supported when a single (non-partitioned) table is specified.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><replaceable class="parameter">boolean</replaceable></term>
+ <listitem>
+ <para>
+ Specifies whether the selected option should be turned on or off.
+ You can write <literal>TRUE</literal>, <literal>ON</literal>, or
+ <literal>1</literal> to enable the option, and <literal>FALSE</literal>,
+ <literal>OFF</literal>, or <literal>0</literal> to disable it. The
+ <replaceable class="parameter">boolean</replaceable> value can also
+ be omitted, in which case <literal>TRUE</literal> is assumed.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </refsect1>
+
+ <refsect1>
+ <title>Notes</title>
+
+ <para>
+ To repack a table, one must have the <literal>MAINTAIN</literal> privilege
+ on the table.
+ </para>
+
+ <para>
+ While <command>REPACK</command> is running, the <xref
+ linkend="guc-search-path"/> is temporarily changed to <literal>pg_catalog,
+ pg_temp</literal>.
+ </para>
+
+ <para>
+ Each backend running <command>REPACK</command> will report its progress
+ in the <structname>pg_stat_progress_repack</structname> view. See
+ <xref linkend="repack-progress-reporting"/> for details.
+ </para>
+
+ <para>
+ Repacking a partitioned table repacks each of its partitions. If an index
+ is specified, each partition is repacked using the partition of that
+ index. <command>REPACK</command> on a partitioned table cannot be executed
+ inside a transaction block.
+ </para>
+
+ </refsect1>
+
+ <refsect1>
+ <title>Examples</title>
+
+ <para>
+ Repack the table <literal>employees</literal>:
+<programlisting>
+REPACK employees;
+</programlisting>
+ </para>
+
+ <para>
+ Repack the table <literal>employees</literal> on the basis of its
+ index <literal>employees_ind</literal> (Since index is used here, this is
+ effectively clustering):
+<programlisting>
+REPACK employees USING INDEX employees_ind;
+</programlisting>
+ </para>
+
+ <para>
+ Repack the table <literal>cases</literal> on physical ordering,
+ running an <command>ANALYZE</command> on the given columns once
+ repacking is done, showing informational messages:
+<programlisting>
+REPACK (ANALYZE, VERBOSE) cases (district, case_nr);
+</programlisting>
+ </para>
+
+ <para>
+ Repack all tables in the database on which you have
+ the <literal>MAINTAIN</literal> privilege:
+<programlisting>
+REPACK;
+</programlisting>
+ </para>
+
+ <para>
+ Repack all tables for which a clustering index has previously been
+ configured on which you have the <literal>MAINTAIN</literal> privilege,
+ showing informational messages:
+<programlisting>
+REPACK (VERBOSE) USING INDEX;
+</programlisting>
+ </para>
+
+ </refsect1>
+
+ <refsect1>
+ <title>Compatibility</title>
+
+ <para>
+ There is no <command>REPACK</command> statement in the SQL standard.
+ </para>
+ </refsect1>
+
+ <refsect1>
+ <title>See Also</title>
+
+ <simplelist type="inline">
+ <member><xref linkend="app-pgrepackdb"/></member>
+ <member><xref linkend="repack-progress-reporting"/></member>
+ </simplelist>
+ </refsect1>
+
+</refentry>
diff --git a/doc/src/sgml/ref/vacuum.sgml b/doc/src/sgml/ref/vacuum.sgml
index 6d0fdd43cfb..ac5d083d468 100644
--- a/doc/src/sgml/ref/vacuum.sgml
+++ b/doc/src/sgml/ref/vacuum.sgml
@@ -25,7 +25,6 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re
<phrase>where <replaceable class="parameter">option</replaceable> can be one of:</phrase>
- FULL [ <replaceable class="parameter">boolean</replaceable> ]
FREEZE [ <replaceable class="parameter">boolean</replaceable> ]
VERBOSE [ <replaceable class="parameter">boolean</replaceable> ]
ANALYZE [ <replaceable class="parameter">boolean</replaceable> ]
@@ -39,6 +38,7 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re
SKIP_DATABASE_STATS [ <replaceable class="parameter">boolean</replaceable> ]
ONLY_DATABASE_STATS [ <replaceable class="parameter">boolean</replaceable> ]
BUFFER_USAGE_LIMIT <replaceable class="parameter">size</replaceable>
+ FULL [ <replaceable class="parameter">boolean</replaceable> ]
<phrase>and <replaceable class="parameter">table_and_columns</replaceable> is:</phrase>
@@ -95,20 +95,6 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re
<title>Parameters</title>
<variablelist>
- <varlistentry>
- <term><literal>FULL</literal></term>
- <listitem>
- <para>
- Selects <quote>full</quote> vacuum, which can reclaim more
- space, but takes much longer and exclusively locks the table.
- This method also requires extra disk space, since it writes a
- new copy of the table and doesn't release the old copy until
- the operation is complete. Usually this should only be used when a
- significant amount of space needs to be reclaimed from within the table.
- </para>
- </listitem>
- </varlistentry>
-
<varlistentry>
<term><literal>FREEZE</literal></term>
<listitem>
@@ -362,6 +348,23 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re
</listitem>
</varlistentry>
+ <varlistentry>
+ <term><literal>FULL</literal></term>
+ <listitem>
+ <para>
+ This option, which is deprecated, makes <command>VACUUM</command>
+ behave like <command>REPACK</command> without a
+ <literal>USING INDEX</literal> clause.
+ This method of compacting the table takes much longer than
+ <command>VACUUM</command> and exclusively locks the table.
+ This method also requires extra disk space, since it writes a
+ new copy of the table and doesn't release the old copy until
+ the operation is complete. Usually this should only be used when a
+ significant amount of space needs to be reclaimed from within the table.
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry>
<term><replaceable class="parameter">boolean</replaceable></term>
<listitem>
diff --git a/doc/src/sgml/reference.sgml b/doc/src/sgml/reference.sgml
index 2cf02c37b17..5d9a8a25a02 100644
--- a/doc/src/sgml/reference.sgml
+++ b/doc/src/sgml/reference.sgml
@@ -195,6 +195,7 @@
&refreshMaterializedView;
&reindex;
&releaseSavepoint;
+ &repack;
&reset;
&revoke;
&rollback;
@@ -258,6 +259,7 @@
&pgIsready;
&pgReceivewal;
&pgRecvlogical;
+ &pgRepackdb;
&pgRestore;
&pgVerifyBackup;
&psqlRef;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index dd4fe6bf62f..b3a19003cdd 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -741,13 +741,13 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
if (OldIndex != NULL && !use_sort)
{
const int ci_index[] = {
- PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_INDEX_RELID
+ PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_INDEX_RELID
};
int64 ci_val[2];
/* Set phase and OIDOldIndex to columns */
- ci_val[0] = PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP;
+ ci_val[0] = PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP;
ci_val[1] = RelationGetRelid(OldIndex);
pgstat_progress_update_multi_param(2, ci_index, ci_val);
@@ -759,15 +759,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
else
{
/* In scan-and-sort mode and also VACUUM FULL, set phase */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP);
tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL);
heapScan = (HeapScanDesc) tableScan;
indexScan = NULL;
/* Set total heap blocks */
- pgstat_progress_update_param(PROGRESS_CLUSTER_TOTAL_HEAP_BLKS,
+ pgstat_progress_update_param(PROGRESS_REPACK_TOTAL_HEAP_BLKS,
heapScan->rs_nblocks);
}
@@ -809,7 +809,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* is manually updated to the correct value when the table
* scan finishes.
*/
- pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED,
heapScan->rs_nblocks);
break;
}
@@ -825,7 +825,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
*/
if (prev_cblock != heapScan->rs_cblock)
{
- pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED,
(heapScan->rs_cblock +
heapScan->rs_nblocks -
heapScan->rs_startblock
@@ -912,14 +912,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* In scan-and-sort mode, report increase in number of tuples
* scanned
*/
- pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_SCANNED,
*num_tuples);
}
else
{
const int ct_index[] = {
- PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED,
- PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN
+ PROGRESS_REPACK_HEAP_TUPLES_SCANNED,
+ PROGRESS_REPACK_HEAP_TUPLES_WRITTEN
};
int64 ct_val[2];
@@ -952,14 +952,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
double n_tuples = 0;
/* Report that we are now sorting tuples */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_SORT_TUPLES);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_SORT_TUPLES);
tuplesort_performsort(tuplesort);
/* Report that we are now writing new heap */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
for (;;)
{
@@ -977,7 +977,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
values, isnull,
rwstate);
/* Report n_tuples */
- pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_WRITTEN,
n_tuples);
}
diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index 8dea58ad96b..bd77584bc99 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -4079,7 +4079,7 @@ reindex_relation(const ReindexStmt *stmt, Oid relid, int flags,
Assert(!ReindexIsProcessingIndex(indexOid));
/* Set index rebuild count */
- pgstat_progress_update_param(PROGRESS_CLUSTER_INDEX_REBUILD_COUNT,
+ pgstat_progress_update_param(PROGRESS_REPACK_INDEX_REBUILD_COUNT,
i);
i++;
}
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 0a0f95f6bb9..6c1461c9ef6 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1283,14 +1283,15 @@ CREATE VIEW pg_stat_progress_vacuum AS
FROM pg_stat_get_progress_info('VACUUM') AS S
LEFT JOIN pg_database D ON S.datid = D.oid;
-CREATE VIEW pg_stat_progress_cluster AS
+CREATE VIEW pg_stat_progress_repack AS
SELECT
S.pid AS pid,
S.datid AS datid,
D.datname AS datname,
S.relid AS relid,
CASE S.param1 WHEN 1 THEN 'CLUSTER'
- WHEN 2 THEN 'VACUUM FULL'
+ WHEN 2 THEN 'REPACK'
+ WHEN 3 THEN 'VACUUM FULL'
END AS command,
CASE S.param2 WHEN 0 THEN 'initializing'
WHEN 1 THEN 'seq scanning heap'
@@ -1301,15 +1302,35 @@ CREATE VIEW pg_stat_progress_cluster AS
WHEN 6 THEN 'rebuilding index'
WHEN 7 THEN 'performing final cleanup'
END AS phase,
- CAST(S.param3 AS oid) AS cluster_index_relid,
+ CAST(S.param3 AS oid) AS repack_index_relid,
S.param4 AS heap_tuples_scanned,
S.param5 AS heap_tuples_written,
S.param6 AS heap_blks_total,
S.param7 AS heap_blks_scanned,
S.param8 AS index_rebuild_count
- FROM pg_stat_get_progress_info('CLUSTER') AS S
+ FROM pg_stat_get_progress_info('REPACK') AS S
LEFT JOIN pg_database D ON S.datid = D.oid;
+-- This view is as the one above, except for renaming a column and avoiding
+-- 'REPACK' as a command name to report.
+CREATE VIEW pg_stat_progress_cluster AS
+ SELECT
+ pid,
+ datid,
+ datname,
+ relid,
+ CASE WHEN command IN ('CLUSTER', 'VACUUM FULL') THEN command
+ WHEN repack_index_relid = 0 THEN 'VACUUM FULL'
+ ELSE 'CLUSTER' END AS command,
+ phase,
+ repack_index_relid AS cluster_index_relid,
+ heap_tuples_scanned,
+ heap_tuples_written,
+ heap_blks_total,
+ heap_blks_scanned,
+ index_rebuild_count
+ FROM pg_stat_progress_repack;
+
CREATE VIEW pg_stat_progress_create_index AS
SELECT
S.pid AS pid, S.datid AS datid, D.datname AS datname,
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 2120c85ccb4..7f772c5c4f8 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1,7 +1,8 @@
/*-------------------------------------------------------------------------
*
* cluster.c
- * CLUSTER a table on an index. This is now also used for VACUUM FULL.
+ * CLUSTER a table on an index. This is now also used for VACUUM FULL and
+ * REPACK.
*
* There is hardly anything left of Paul Brown's original implementation...
*
@@ -67,27 +68,36 @@ typedef struct
Oid indexOid;
} RelToCluster;
-
-static void cluster_multiple_rels(List *rtcs, ClusterParams *params);
-static void rebuild_relation(Relation OldHeap, Relation index, bool verbose);
+static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap,
+ Oid indexOid, Oid userid, int options);
+static void rebuild_relation(RepackCommand cmd,
+ Relation OldHeap, Relation index, bool verbose);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
bool verbose, bool *pSwapToastByContent,
TransactionId *pFreezeXid, MultiXactId *pCutoffMulti);
-static List *get_tables_to_cluster(MemoryContext cluster_context);
-static List *get_tables_to_cluster_partitioned(MemoryContext cluster_context,
- Oid indexOid);
-static bool cluster_is_permitted_for_relation(Oid relid, Oid userid);
+static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
+ MemoryContext permcxt);
+static List *get_tables_to_repack_partitioned(RepackCommand cmd,
+ Oid relid, bool rel_is_index,
+ MemoryContext permcxt);
+static bool cluster_is_permitted_for_relation(RepackCommand cmd,
+ Oid relid, Oid userid);
+static Relation process_single_relation(RepackStmt *stmt,
+ ClusterParams *params);
+static Oid determine_clustered_index(Relation rel, bool usingindex,
+ const char *indexname);
+static const char *RepackCommandAsString(RepackCommand cmd);
-/*---------------------------------------------------------------------------
- * This cluster code allows for clustering multiple tables at once. Because
+/*
+ * The repack code allows for processing multiple tables at once. Because
* of this, we cannot just run everything on a single transaction, or we
* would be forced to acquire exclusive locks on all the tables being
* clustered, simultaneously --- very likely leading to deadlock.
*
- * To solve this we follow a similar strategy to VACUUM code,
- * clustering each relation in a separate transaction. For this to work,
- * we need to:
+ * To solve this we follow a similar strategy to VACUUM code, processing each
+ * relation in a separate transaction. For this to work, we need to:
+ *
* - provide a separate memory context so that we can pass information in
* a way that survives across transactions
* - start a new transaction every time a new relation is clustered
@@ -98,197 +108,165 @@ static bool cluster_is_permitted_for_relation(Oid relid, Oid userid);
*
* The single-relation case does not have any such overhead.
*
- * We also allow a relation to be specified without index. In that case,
- * the indisclustered bit will be looked up, and an ERROR will be thrown
- * if there is no index with the bit set.
- *---------------------------------------------------------------------------
+ * We also allow a relation to be repacked following an index, but without
+ * naming a specific one. In that case, the indisclustered bit will be
+ * looked up, and an ERROR will be thrown if no so-marked index is found.
*/
void
-cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
+ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
{
- ListCell *lc;
ClusterParams params = {0};
- bool verbose = false;
Relation rel = NULL;
- Oid indexOid = InvalidOid;
- MemoryContext cluster_context;
+ MemoryContext repack_context;
List *rtcs;
/* Parse option list */
- foreach(lc, stmt->params)
+ foreach_node(DefElem, opt, stmt->params)
{
- DefElem *opt = (DefElem *) lfirst(lc);
-
if (strcmp(opt->defname, "verbose") == 0)
- verbose = defGetBoolean(opt);
+ params.options |= defGetBoolean(opt) ? CLUOPT_VERBOSE : 0;
+ else if (strcmp(opt->defname, "analyze") == 0 ||
+ strcmp(opt->defname, "analyse") == 0)
+ params.options |= defGetBoolean(opt) ? CLUOPT_ANALYZE : 0;
else
ereport(ERROR,
- (errcode(ERRCODE_SYNTAX_ERROR),
- errmsg("unrecognized %s option \"%s\"",
- "CLUSTER", opt->defname),
- parser_errposition(pstate, opt->location)));
+ errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("unrecognized %s option \"%s\"",
+ RepackCommandAsString(stmt->command),
+ opt->defname),
+ parser_errposition(pstate, opt->location));
}
- params.options = (verbose ? CLUOPT_VERBOSE : 0);
-
+ /*
+ * 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.
+ */
if (stmt->relation != NULL)
{
- /* This is the single-relation case. */
- Oid tableOid;
-
- /*
- * Find, lock, and check permissions on the table. We obtain
- * AccessExclusiveLock right away to avoid lock-upgrade hazard in the
- * single-transaction case.
- */
- tableOid = RangeVarGetRelidExtended(stmt->relation,
- AccessExclusiveLock,
- 0,
- RangeVarCallbackMaintainsTable,
- NULL);
- rel = table_open(tableOid, NoLock);
-
- /*
- * Reject clustering a remote temp table ... their local buffer
- * manager is not going to cope.
- */
- if (RELATION_IS_OTHER_TEMP(rel))
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("cannot cluster temporary tables of other sessions")));
-
- if (stmt->indexname == NULL)
- {
- ListCell *index;
-
- /* We need to find the index that has indisclustered set. */
- foreach(index, RelationGetIndexList(rel))
- {
- indexOid = lfirst_oid(index);
- if (get_index_isclustered(indexOid))
- break;
- indexOid = InvalidOid;
- }
-
- if (!OidIsValid(indexOid))
- ereport(ERROR,
- (errcode(ERRCODE_UNDEFINED_OBJECT),
- errmsg("there is no previously clustered index for table \"%s\"",
- stmt->relation->relname)));
- }
- else
- {
- /*
- * The index is expected to be in the same namespace as the
- * relation.
- */
- indexOid = get_relname_relid(stmt->indexname,
- rel->rd_rel->relnamespace);
- if (!OidIsValid(indexOid))
- ereport(ERROR,
- (errcode(ERRCODE_UNDEFINED_OBJECT),
- errmsg("index \"%s\" for table \"%s\" does not exist",
- stmt->indexname, stmt->relation->relname)));
- }
-
- /* For non-partitioned tables, do what we came here to do. */
- if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
- {
- cluster_rel(rel, indexOid, ¶ms);
- /* cluster_rel closes the relation, but keeps lock */
-
- return;
- }
+ rel = process_single_relation(stmt, ¶ms);
+ if (rel == NULL)
+ return; /* all done */
}
+ /*
+ * Don't allow ANALYZE in the multiple-relation case for now. Maybe we
+ * can add support for this later.
+ */
+ if (params.options & CLUOPT_ANALYZE)
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot %s multiple tables", "REPACK (ANALYZE)"));
+
/*
* By here, we know we are in a multi-table situation. In order to avoid
* holding locks for too long, we want to process each table in its own
* transaction. This forces us to disallow running inside a user
* transaction block.
*/
- PreventInTransactionBlock(isTopLevel, "CLUSTER");
+ PreventInTransactionBlock(isTopLevel, RepackCommandAsString(stmt->command));
/* Also, we need a memory context to hold our list of relations */
- cluster_context = AllocSetContextCreate(PortalContext,
- "Cluster",
- ALLOCSET_DEFAULT_SIZES);
+ repack_context = AllocSetContextCreate(PortalContext,
+ "Repack",
+ ALLOCSET_DEFAULT_SIZES);
+
+ params.options |= CLUOPT_RECHECK;
/*
- * Either we're processing a partitioned table, or we were not given any
- * table name at all. In either case, obtain a list of relations to
- * process.
- *
- * In the former case, an index name must have been given, so we don't
- * need to recheck its "indisclustered" bit, but we have to check that it
- * is an index that we can cluster on. In the latter case, we set the
- * option bit to have indisclustered verified.
- *
- * Rechecking the relation itself is necessary here in all cases.
+ * If we don't have a relation yet, determine a relation list. If we do,
+ * then it must be a partitioned table, and we want to process its
+ * partitions.
*/
- params.options |= CLUOPT_RECHECK;
- if (rel != NULL)
+ if (rel == NULL)
{
- Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
- check_index_is_clusterable(rel, indexOid, AccessShareLock);
- rtcs = get_tables_to_cluster_partitioned(cluster_context, indexOid);
-
- /* close relation, releasing lock on parent table */
- table_close(rel, AccessExclusiveLock);
+ Assert(stmt->indexname == NULL);
+ rtcs = get_tables_to_repack(stmt->command, stmt->usingindex,
+ repack_context);
}
else
{
- rtcs = get_tables_to_cluster(cluster_context);
- params.options |= CLUOPT_RECHECK_ISCLUSTERED;
- }
+ Oid relid;
+ bool rel_is_index;
- /* Do the job. */
- cluster_multiple_rels(rtcs, ¶ms);
+ Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
- /* Start a new transaction for the cleanup work. */
- StartTransactionCommand();
+ /*
+ * If USING INDEX was specified, resolve the index name now and pass
+ * it down.
+ */
+ if (stmt->usingindex)
+ {
+ /*
+ * If no index name was specified when repacking a partitioned
+ * table, punt for now. Maybe we can improve this later.
+ */
+ if (!stmt->indexname)
+ ereport(ERROR,
+ errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("there is no previously clustered index for table \"%s\"",
+ RelationGetRelationName(rel)));
+
+ relid = determine_clustered_index(rel, stmt->usingindex,
+ stmt->indexname);
+ if (!OidIsValid(relid))
+ elog(ERROR, "unable to determine index to cluster on");
+ /* XXX is this the right place for this check? */
+ check_index_is_clusterable(rel, relid, AccessExclusiveLock);
+ rel_is_index = true;
+ }
+ else
+ {
+ relid = RelationGetRelid(rel);
+ rel_is_index = false;
+ }
- /* Clean up working storage */
- MemoryContextDelete(cluster_context);
-}
+ rtcs = get_tables_to_repack_partitioned(stmt->command,
+ relid, rel_is_index,
+ repack_context);
-/*
- * Given a list of relations to cluster, process each of them in a separate
- * transaction.
- *
- * We expect to be in a transaction at start, but there isn't one when we
- * return.
- */
-static void
-cluster_multiple_rels(List *rtcs, ClusterParams *params)
-{
- ListCell *lc;
+ /* close parent relation, releasing lock on it */
+ table_close(rel, AccessExclusiveLock);
+ rel = NULL;
+ }
/* Commit to get out of starting transaction */
PopActiveSnapshot();
CommitTransactionCommand();
/* Cluster the tables, each in a separate transaction */
- foreach(lc, rtcs)
+ Assert(rel == NULL);
+ foreach_ptr(RelToCluster, rtc, rtcs)
{
- RelToCluster *rtc = (RelToCluster *) lfirst(lc);
- Relation rel;
-
/* Start a new transaction for each relation. */
StartTransactionCommand();
+ /*
+ * Open the target table, coping with the case where it has been
+ * dropped.
+ */
+ rel = try_table_open(rtc->tableOid, AccessExclusiveLock);
+ if (rel == NULL)
+ {
+ CommitTransactionCommand();
+ continue;
+ }
+
/* functions in indexes may want a snapshot set */
PushActiveSnapshot(GetTransactionSnapshot());
- rel = table_open(rtc->tableOid, AccessExclusiveLock);
-
/* Process this table */
- cluster_rel(rel, rtc->indexOid, params);
+ cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms);
/* cluster_rel closes the relation, but keeps lock */
PopActiveSnapshot();
CommitTransactionCommand();
}
+
+ /* Start a new transaction for the cleanup work. */
+ StartTransactionCommand();
+
+ /* Clean up working storage */
+ MemoryContextDelete(repack_context);
}
/*
@@ -304,11 +282,14 @@ cluster_multiple_rels(List *rtcs, ClusterParams *params)
* them incrementally while we load the table.
*
* If indexOid is InvalidOid, the table will be rewritten in physical order
- * instead of index order. This is the new implementation of VACUUM FULL,
- * and error messages should refer to the operation as VACUUM not CLUSTER.
+ * instead of index order.
+ *
+ * 'cmd' indicates which command is being executed, to be used for error
+ * messages.
*/
void
-cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params)
+cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
+ ClusterParams *params)
{
Oid tableOid = RelationGetRelid(OldHeap);
Oid save_userid;
@@ -323,13 +304,8 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params)
/* Check for user-requested abort. */
CHECK_FOR_INTERRUPTS();
- pgstat_progress_start_command(PROGRESS_COMMAND_CLUSTER, tableOid);
- if (OidIsValid(indexOid))
- pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND,
- PROGRESS_CLUSTER_COMMAND_CLUSTER);
- else
- pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND,
- PROGRESS_CLUSTER_COMMAND_VACUUM_FULL);
+ pgstat_progress_start_command(PROGRESS_COMMAND_REPACK, tableOid);
+ pgstat_progress_update_param(PROGRESS_REPACK_COMMAND, cmd);
/*
* Switch to the table owner's userid, so that any index functions are run
@@ -350,86 +326,38 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params)
* *must* skip the one on indisclustered since it would reject an attempt
* to cluster a not-previously-clustered index.
*/
- if (recheck)
- {
- /* Check that the user still has privileges for the relation */
- if (!cluster_is_permitted_for_relation(tableOid, save_userid))
- {
- relation_close(OldHeap, AccessExclusiveLock);
- goto out;
- }
-
- /*
- * Silently skip a temp table for a remote session. Only doing this
- * check in the "recheck" case is appropriate (which currently means
- * somebody is executing a database-wide CLUSTER or on a partitioned
- * table), because there is another check in cluster() which will stop
- * any attempt to cluster remote temp tables by name. There is
- * another check in cluster_rel which is redundant, but we leave it
- * for extra safety.
- */
- if (RELATION_IS_OTHER_TEMP(OldHeap))
- {
- relation_close(OldHeap, AccessExclusiveLock);
- goto out;
- }
-
- if (OidIsValid(indexOid))
- {
- /*
- * Check that the index still exists
- */
- if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid)))
- {
- relation_close(OldHeap, AccessExclusiveLock);
- goto out;
- }
-
- /*
- * Check that the index is still the one with indisclustered set,
- * if needed.
- */
- if ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
- !get_index_isclustered(indexOid))
- {
- relation_close(OldHeap, AccessExclusiveLock);
- goto out;
- }
- }
- }
+ if (recheck &&
+ !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid,
+ params->options))
+ goto out;
/*
- * We allow VACUUM FULL, but not CLUSTER, on shared catalogs. CLUSTER
- * would work in most respects, but the index would only get marked as
- * indisclustered in the current database, leading to unexpected behavior
- * if CLUSTER were later invoked in another database.
+ * We allow repacking shared catalogs only when not using an index. It
+ * would work to use an index in most respects, but the index would only
+ * get marked as indisclustered in the current database, leading to
+ * unexpected behavior if CLUSTER were later invoked in another database.
*/
if (OidIsValid(indexOid) && OldHeap->rd_rel->relisshared)
ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("cannot cluster a shared catalog")));
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot run %s on a shared catalog",
+ RepackCommandAsString(cmd)));
/*
* Don't process temp tables of other backends ... their local buffer
* manager is not going to cope.
*/
if (RELATION_IS_OTHER_TEMP(OldHeap))
- {
- if (OidIsValid(indexOid))
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("cannot cluster temporary tables of other sessions")));
- else
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("cannot vacuum temporary tables of other sessions")));
- }
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot run %s on temporary tables of other sessions",
+ RepackCommandAsString(cmd)));
/*
* Also check for active uses of the relation in the current transaction,
* including open scans and pending AFTER trigger events.
*/
- CheckTableNotInUse(OldHeap, OidIsValid(indexOid) ? "CLUSTER" : "VACUUM");
+ CheckTableNotInUse(OldHeap, RepackCommandAsString(cmd));
/* Check heap and index are valid to cluster on */
if (OidIsValid(indexOid))
@@ -442,6 +370,24 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params)
else
index = NULL;
+ /*
+ * When allow_system_table_mods is turned off, we disallow repacking a
+ * catalog on a particular index unless that's already the clustered index
+ * for that catalog.
+ *
+ * XXX We don't check for this in CLUSTER, because it's historically been
+ * allowed.
+ */
+ if (cmd != REPACK_COMMAND_CLUSTER &&
+ !allowSystemTableMods && OidIsValid(indexOid) &&
+ IsCatalogRelation(OldHeap) && !index->rd_index->indisclustered)
+ ereport(ERROR,
+ errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+ errmsg("permission denied: \"%s\" is a system catalog",
+ RelationGetRelationName(OldHeap)),
+ errdetail("System catalogs can only be clustered by the index they're already clustered on, if any, unless \"%s\" is enabled.",
+ "allow_system_table_mods"));
+
/*
* Quietly ignore the request if this is a materialized view which has not
* been populated from its query. No harm is done because there is no data
@@ -469,7 +415,7 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params)
TransferPredicateLocksToHeapRelation(OldHeap);
/* rebuild_relation does all the dirty work */
- rebuild_relation(OldHeap, index, verbose);
+ rebuild_relation(cmd, OldHeap, index, verbose);
/* rebuild_relation closes OldHeap, and index if valid */
out:
@@ -482,6 +428,63 @@ out:
pgstat_progress_end_command();
}
+/*
+ * Check if the table (and its index) still meets the requirements of
+ * cluster_rel().
+ */
+static bool
+cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
+ Oid userid, int options)
+{
+ Oid tableOid = RelationGetRelid(OldHeap);
+
+ /* Check that the user still has privileges for the relation */
+ if (!cluster_is_permitted_for_relation(cmd, tableOid, userid))
+ {
+ relation_close(OldHeap, AccessExclusiveLock);
+ return false;
+ }
+
+ /*
+ * Silently skip a temp table for a remote session. Only doing this check
+ * in the "recheck" case is appropriate (which currently means somebody is
+ * executing a database-wide CLUSTER or on a partitioned table), because
+ * there is another check in cluster() which will stop any attempt to
+ * cluster remote temp tables by name. There is another check in
+ * cluster_rel which is redundant, but we leave it for extra safety.
+ */
+ if (RELATION_IS_OTHER_TEMP(OldHeap))
+ {
+ relation_close(OldHeap, AccessExclusiveLock);
+ return false;
+ }
+
+ if (OidIsValid(indexOid))
+ {
+ /*
+ * Check that the index still exists
+ */
+ if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid)))
+ {
+ relation_close(OldHeap, AccessExclusiveLock);
+ return false;
+ }
+
+ /*
+ * Check that the index is still the one with indisclustered set, if
+ * needed.
+ */
+ if ((options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+ !get_index_isclustered(indexOid))
+ {
+ relation_close(OldHeap, AccessExclusiveLock);
+ return false;
+ }
+ }
+
+ return true;
+}
+
/*
* Verify that the specified heap and index are valid to cluster on
*
@@ -626,7 +629,8 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
* On exit, they are closed, but locks on them are not released.
*/
static void
-rebuild_relation(Relation OldHeap, Relation index, bool verbose)
+rebuild_relation(RepackCommand cmd,
+ Relation OldHeap, Relation index, bool verbose)
{
Oid tableOid = RelationGetRelid(OldHeap);
Oid accessMethod = OldHeap->rd_rel->relam;
@@ -642,8 +646,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false) &&
(index == NULL || CheckRelationLockedByMe(index, AccessExclusiveLock, false)));
- if (index)
- /* Mark the correct index as clustered */
+ /* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */
+ if (index != NULL)
mark_index_clustered(OldHeap, RelationGetRelid(index), true);
/* Remember info about rel before closing OldHeap */
@@ -958,20 +962,20 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
/* Log what we're doing */
if (OldIndex != NULL && !use_sort)
ereport(elevel,
- (errmsg("clustering \"%s.%s\" using index scan on \"%s\"",
- nspname,
- RelationGetRelationName(OldHeap),
- RelationGetRelationName(OldIndex))));
+ errmsg("repacking \"%s.%s\" using index scan on \"%s\"",
+ nspname,
+ RelationGetRelationName(OldHeap),
+ RelationGetRelationName(OldIndex)));
else if (use_sort)
ereport(elevel,
- (errmsg("clustering \"%s.%s\" using sequential scan and sort",
- nspname,
- RelationGetRelationName(OldHeap))));
+ errmsg("repacking \"%s.%s\" using sequential scan and sort",
+ nspname,
+ RelationGetRelationName(OldHeap)));
else
ereport(elevel,
- (errmsg("vacuuming \"%s.%s\"",
- nspname,
- RelationGetRelationName(OldHeap))));
+ errmsg("repacking \"%s.%s\" in physical order",
+ nspname,
+ RelationGetRelationName(OldHeap)));
/*
* Hand off the actual copying to AM specific function, the generic code
@@ -1458,8 +1462,8 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
int i;
/* Report that we are now swapping relation files */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_SWAP_REL_FILES);
/* Zero out possible results from swapped_relation_files */
memset(mapped_tables, 0, sizeof(mapped_tables));
@@ -1509,14 +1513,14 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
/* Report that we are now reindexing relations */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_REBUILD_INDEX);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_REBUILD_INDEX);
reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params);
/* Report that we are now doing clean up */
- pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE,
- PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
/*
* If the relation being rebuilt is pg_class, swap_relation_files()
@@ -1632,106 +1636,191 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
}
}
-
/*
- * Get a list of tables that the current user has privileges on and
- * have indisclustered set. Return the list in a List * of RelToCluster
- * (stored in the specified memory context), each one giving the tableOid
- * and the indexOid on which the table is already clustered.
+ * Determine which relations to process, when REPACK/CLUSTER is called
+ * without specifying a table name. The exact process depends on whether
+ * USING INDEX was given or not, and in any case we only return tables and
+ * materialized views that the current user has privileges to repack/cluster.
+ *
+ * If USING INDEX was given, we scan pg_index to find those that have
+ * indisclustered set; if it was not given, scan pg_class and return all
+ * tables.
+ *
+ * Return it as a list of RelToCluster in the given memory context.
*/
static List *
-get_tables_to_cluster(MemoryContext cluster_context)
+get_tables_to_repack(RepackCommand cmd, bool usingindex, MemoryContext permcxt)
{
- Relation indRelation;
+ Relation catalog;
TableScanDesc scan;
- ScanKeyData entry;
- HeapTuple indexTuple;
- Form_pg_index index;
- MemoryContext old_context;
+ HeapTuple tuple;
List *rtcs = NIL;
- /*
- * Get all indexes that have indisclustered set and that the current user
- * has the appropriate privileges for.
- */
- indRelation = table_open(IndexRelationId, AccessShareLock);
- ScanKeyInit(&entry,
- Anum_pg_index_indisclustered,
- BTEqualStrategyNumber, F_BOOLEQ,
- BoolGetDatum(true));
- scan = table_beginscan_catalog(indRelation, 1, &entry);
- while ((indexTuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
+ if (usingindex)
{
- RelToCluster *rtc;
+ ScanKeyData entry;
+
+ catalog = table_open(IndexRelationId, AccessShareLock);
+ ScanKeyInit(&entry,
+ Anum_pg_index_indisclustered,
+ BTEqualStrategyNumber, F_BOOLEQ,
+ BoolGetDatum(true));
+ scan = table_beginscan_catalog(catalog, 1, &entry);
+ while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
+ {
+ RelToCluster *rtc;
+ Form_pg_index index;
+ MemoryContext oldcxt;
- index = (Form_pg_index) GETSTRUCT(indexTuple);
+ index = (Form_pg_index) GETSTRUCT(tuple);
- if (!cluster_is_permitted_for_relation(index->indrelid, GetUserId()))
- continue;
+ /*
+ * Try to obtain a light lock on the index's table, to ensure it
+ * doesn't go away while we collect the list. If we cannot, just
+ * disregard it.
+ */
+ if (!ConditionalLockRelationOid(index->indrelid, AccessShareLock))
+ continue;
- /* Use a permanent memory context for the result list */
- old_context = MemoryContextSwitchTo(cluster_context);
+ /* Verify that the table still exists */
+ if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(index->indrelid)))
+ {
+ /* Release useless lock */
+ UnlockRelationOid(index->indrelid, AccessShareLock);
+ continue;
+ }
- rtc = palloc_object(RelToCluster);
- rtc->tableOid = index->indrelid;
- rtc->indexOid = index->indexrelid;
- rtcs = lappend(rtcs, rtc);
+ if (!cluster_is_permitted_for_relation(cmd, index->indrelid,
+ GetUserId()))
+ continue;
+
+ /* Use a permanent memory context for the result list */
+ oldcxt = MemoryContextSwitchTo(permcxt);
+ rtc = palloc_object(RelToCluster);
+ rtc->tableOid = index->indrelid;
+ rtc->indexOid = index->indexrelid;
+ rtcs = lappend(rtcs, rtc);
+ MemoryContextSwitchTo(oldcxt);
+ }
+ }
+ else
+ {
+ catalog = table_open(RelationRelationId, AccessShareLock);
+ scan = table_beginscan_catalog(catalog, 0, NULL);
+
+ while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
+ {
+ RelToCluster *rtc;
+ Form_pg_class class;
+ MemoryContext oldcxt;
+
+ class = (Form_pg_class) GETSTRUCT(tuple);
+
+ /*
+ * Try to obtain a light lock on the table, to ensure it doesn't
+ * go away while we collect the list. If we cannot, just
+ * disregard the table.
+ */
+ if (!ConditionalLockRelationOid(class->oid, AccessShareLock))
+ continue;
- MemoryContextSwitchTo(old_context);
+ /* Verify that the table still exists */
+ if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(class->oid)))
+ {
+ /* Release useless lock */
+ UnlockRelationOid(class->oid, AccessShareLock);
+ continue;
+ }
+
+ /* Can only process plain tables and matviews */
+ if (class->relkind != RELKIND_RELATION &&
+ class->relkind != RELKIND_MATVIEW)
+ continue;
+
+ /* noisily skip rels which the user can't process */
+ if (!cluster_is_permitted_for_relation(cmd, class->oid,
+ GetUserId()))
+ continue;
+
+ /* Use a permanent memory context for the result list */
+ oldcxt = MemoryContextSwitchTo(permcxt);
+ rtc = palloc_object(RelToCluster);
+ rtc->tableOid = class->oid;
+ rtc->indexOid = InvalidOid;
+ rtcs = lappend(rtcs, rtc);
+ MemoryContextSwitchTo(oldcxt);
+ }
}
- table_endscan(scan);
- relation_close(indRelation, AccessShareLock);
+ table_endscan(scan);
+ relation_close(catalog, AccessShareLock);
return rtcs;
}
/*
- * Given an index on a partitioned table, return a list of RelToCluster for
+ * Given a partitioned table or its index, return a list of RelToCluster for
* all the children leaves tables/indexes.
*
* Like expand_vacuum_rel, but here caller must hold AccessExclusiveLock
* on the table containing the index.
+ *
+ * 'rel_is_index' tells whether 'relid' is that of an index (true) or of the
+ * owning relation.
*/
static List *
-get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid)
+get_tables_to_repack_partitioned(RepackCommand cmd, Oid relid,
+ bool rel_is_index, MemoryContext permcxt)
{
List *inhoids;
- ListCell *lc;
List *rtcs = NIL;
- MemoryContext old_context;
- /* Do not lock the children until they're processed */
- inhoids = find_all_inheritors(indexOid, NoLock, NULL);
-
- foreach(lc, inhoids)
+ /*
+ * Do not lock the children until they're processed. Note that we do hold
+ * a lock on the parent partitioned table.
+ */
+ inhoids = find_all_inheritors(relid, NoLock, NULL);
+ foreach_oid(child_oid, inhoids)
{
- Oid indexrelid = lfirst_oid(lc);
- Oid relid = IndexGetRelation(indexrelid, false);
+ Oid table_oid,
+ index_oid;
RelToCluster *rtc;
+ MemoryContext oldcxt;
- /* consider only leaf indexes */
- if (get_rel_relkind(indexrelid) != RELKIND_INDEX)
- continue;
+ if (rel_is_index)
+ {
+ /* consider only leaf indexes */
+ if (get_rel_relkind(child_oid) != RELKIND_INDEX)
+ continue;
+
+ table_oid = IndexGetRelation(child_oid, false);
+ index_oid = child_oid;
+ }
+ else
+ {
+ /* consider only leaf relations */
+ if (get_rel_relkind(child_oid) != RELKIND_RELATION)
+ continue;
+
+ table_oid = child_oid;
+ index_oid = InvalidOid;
+ }
/*
* It's possible that the user does not have privileges to CLUSTER the
- * leaf partition despite having such privileges on the partitioned
- * table. We skip any partitions which the user is not permitted to
- * CLUSTER.
+ * leaf partition despite having them on the partitioned table. Skip
+ * if so.
*/
- if (!cluster_is_permitted_for_relation(relid, GetUserId()))
+ if (!cluster_is_permitted_for_relation(cmd, table_oid, GetUserId()))
continue;
/* Use a permanent memory context for the result list */
- old_context = MemoryContextSwitchTo(cluster_context);
-
+ oldcxt = MemoryContextSwitchTo(permcxt);
rtc = palloc_object(RelToCluster);
- rtc->tableOid = relid;
- rtc->indexOid = indexrelid;
+ rtc->tableOid = table_oid;
+ rtc->indexOid = index_oid;
rtcs = lappend(rtcs, rtc);
-
- MemoryContextSwitchTo(old_context);
+ MemoryContextSwitchTo(oldcxt);
}
return rtcs;
@@ -1742,13 +1831,167 @@ get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid)
* function emits a WARNING.
*/
static bool
-cluster_is_permitted_for_relation(Oid relid, Oid userid)
+cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid)
{
+ Assert(cmd == REPACK_COMMAND_CLUSTER || cmd == REPACK_COMMAND_REPACK);
+
if (pg_class_aclcheck(relid, userid, ACL_MAINTAIN) == ACLCHECK_OK)
return true;
ereport(WARNING,
- (errmsg("permission denied to cluster \"%s\", skipping it",
- get_rel_name(relid))));
+ errmsg("permission denied to execute %s on \"%s\", skipping it",
+ RepackCommandAsString(cmd),
+ get_rel_name(relid)));
+
return false;
}
+
+
+/*
+ * Given a RepackStmt with an indicated relation name, resolve the relation
+ * name, obtain lock on it, then determine what to do based on the relation
+ * type: if it's table and not partitioned, repack it as indicated (using an
+ * existing clustered index, or following the given one), and return NULL.
+ *
+ * On the other hand, if the table is partitioned, do nothing further and
+ * instead return the opened and locked relcache entry, so that caller can
+ * process the partitions using the multiple-table handling code. In this
+ * case, if an index name is given, it's up to the caller to resolve it.
+ */
+static Relation
+process_single_relation(RepackStmt *stmt, ClusterParams *params)
+{
+ Relation rel;
+ Oid tableOid;
+
+ Assert(stmt->relation != NULL);
+ Assert(stmt->command == REPACK_COMMAND_CLUSTER ||
+ stmt->command == REPACK_COMMAND_REPACK);
+
+ /*
+ * Find, lock, and check permissions on the table. We obtain
+ * AccessExclusiveLock right away to avoid lock-upgrade hazard in the
+ * single-transaction case.
+ */
+ tableOid = RangeVarGetRelidExtended(stmt->relation->relation,
+ AccessExclusiveLock,
+ 0,
+ RangeVarCallbackMaintainsTable,
+ NULL);
+ rel = table_open(tableOid, NoLock);
+
+ /*
+ * Reject clustering a remote temp table ... their local buffer manager is
+ * not going to cope.
+ */
+ if (RELATION_IS_OTHER_TEMP(rel))
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot execute %s on temporary tables of other sessions",
+ RepackCommandAsString(stmt->command)));
+
+ /*
+ * Make sure ANALYZE is specified if a column list is present.
+ */
+ if ((params->options & CLUOPT_ANALYZE) == 0 && stmt->relation->va_cols != NIL)
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("ANALYZE option must be specified when a column list is provided"));
+
+ /*
+ * For partitioned tables, let caller handle this. Otherwise, process it
+ * here and we're done.
+ */
+ if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
+ return rel;
+ else
+ {
+ Oid indexOid;
+
+ indexOid = determine_clustered_index(rel, stmt->usingindex,
+ stmt->indexname);
+ if (OidIsValid(indexOid))
+ check_index_is_clusterable(rel, indexOid, AccessExclusiveLock);
+ cluster_rel(stmt->command, rel, indexOid, params);
+
+ /* Do an analyze, if requested */
+ if (params->options & CLUOPT_ANALYZE)
+ {
+ VacuumParams vac_params = {0};
+
+ vac_params.options |= VACOPT_ANALYZE;
+ if (params->options & CLUOPT_VERBOSE)
+ vac_params.options |= VACOPT_VERBOSE;
+ analyze_rel(tableOid, NULL, vac_params,
+ stmt->relation->va_cols, true, NULL);
+ }
+
+ return NULL;
+ }
+}
+
+/*
+ * Given a relation and the usingindex/indexname options in a
+ * REPACK USING INDEX or CLUSTER command, return the OID of the
+ * index to use for clustering the table.
+ *
+ * Caller must hold lock on the relation so that the set of indexes
+ * doesn't change, and must call check_index_is_clusterable.
+ */
+static Oid
+determine_clustered_index(Relation rel, bool usingindex, const char *indexname)
+{
+ Oid indexOid;
+
+ if (indexname == NULL && usingindex)
+ {
+ /*
+ * If USING INDEX with no name is given, find a clustered index, or
+ * error out if none.
+ */
+ indexOid = InvalidOid;
+ foreach_oid(idxoid, RelationGetIndexList(rel))
+ {
+ if (get_index_isclustered(idxoid))
+ {
+ indexOid = idxoid;
+ break;
+ }
+ }
+
+ if (!OidIsValid(indexOid))
+ ereport(ERROR,
+ errcode(ERRCODE_UNDEFINED_OBJECT),
+ errmsg("there is no previously clustered index for table \"%s\"",
+ RelationGetRelationName(rel)));
+ }
+ else if (indexname != NULL)
+ {
+ /* An index was specified; obtain its OID. */
+ indexOid = get_relname_relid(indexname, rel->rd_rel->relnamespace);
+ if (!OidIsValid(indexOid))
+ ereport(ERROR,
+ errcode(ERRCODE_UNDEFINED_OBJECT),
+ errmsg("index \"%s\" for table \"%s\" does not exist",
+ indexname, RelationGetRelationName(rel)));
+ }
+ else
+ indexOid = InvalidOid;
+
+ return indexOid;
+}
+
+static const char *
+RepackCommandAsString(RepackCommand cmd)
+{
+ switch (cmd)
+ {
+ case REPACK_COMMAND_REPACK:
+ return "REPACK";
+ case REPACK_COMMAND_VACUUMFULL:
+ return "VACUUM";
+ case REPACK_COMMAND_CLUSTER:
+ return "CLUSTER";
+ }
+ return "???";
+}
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index 0528d1b6ecb..6afa203983f 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -351,7 +351,6 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel)
}
}
-
/*
* Sanity check DISABLE_PAGE_SKIPPING option.
*/
@@ -2289,8 +2288,9 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
if ((params.options & VACOPT_VERBOSE) != 0)
cluster_params.options |= CLUOPT_VERBOSE;
- /* VACUUM FULL is now a variant of CLUSTER; see cluster.c */
- cluster_rel(rel, InvalidOid, &cluster_params);
+ /* VACUUM FULL is a variant of REPACK; see cluster.c */
+ cluster_rel(REPACK_COMMAND_VACUUMFULL, rel, InvalidOid,
+ &cluster_params);
/* cluster_rel closes the relation, but keeps lock */
rel = NULL;
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 7856ce9d78f..ff336a1adf8 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -286,7 +286,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
AlterCompositeTypeStmt AlterUserMappingStmt
AlterRoleStmt AlterRoleSetStmt AlterPolicyStmt AlterStatsStmt
AlterDefaultPrivilegesStmt DefACLAction
- AnalyzeStmt CallStmt ClosePortalStmt ClusterStmt CommentStmt
+ AnalyzeStmt CallStmt ClosePortalStmt CommentStmt
ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt
CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt
@@ -303,7 +303,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
GrantStmt GrantRoleStmt ImportForeignSchemaStmt IndexStmt InsertStmt
ListenStmt LoadStmt LockStmt MergeStmt NotifyStmt ExplainableStmt PreparableStmt
CreateFunctionStmt AlterFunctionStmt ReindexStmt RemoveAggrStmt
- RemoveFuncStmt RemoveOperStmt RenameStmt ReturnStmt RevokeStmt RevokeRoleStmt
+ RemoveFuncStmt RemoveOperStmt RenameStmt RepackStmt ReturnStmt RevokeStmt RevokeRoleStmt
RuleActionStmt RuleActionStmtOrEmpty RuleStmt
SecLabelStmt SelectStmt TransactionStmt TransactionStmtLegacy TruncateStmt
UnlistenStmt UpdateStmt VacuumStmt
@@ -322,7 +322,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
%type <str> opt_single_name
%type <list> opt_qualified_name
-%type <boolean> opt_concurrently
+%type <boolean> opt_concurrently opt_usingindex
%type <dbehavior> opt_drop_behavior
%type <list> opt_utility_option_list
%type <list> opt_wait_with_clause
@@ -770,7 +770,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
QUOTE QUOTES
RANGE READ REAL REASSIGN RECURSIVE REF_P REFERENCES REFERENCING
- REFRESH REINDEX RELATIVE_P RELEASE RENAME REPEATABLE REPLACE REPLICA
+ REFRESH REINDEX RELATIVE_P RELEASE RENAME REPACK REPEATABLE REPLACE REPLICA
RESET RESPECT_P RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
ROUTINE ROUTINES ROW ROWS RULE
@@ -1032,7 +1032,6 @@ stmt:
| CallStmt
| CheckPointStmt
| ClosePortalStmt
- | ClusterStmt
| CommentStmt
| ConstraintsSetStmt
| CopyStmt
@@ -1106,6 +1105,7 @@ stmt:
| RemoveFuncStmt
| RemoveOperStmt
| RenameStmt
+ | RepackStmt
| RevokeStmt
| RevokeRoleStmt
| RuleStmt
@@ -1143,6 +1143,11 @@ opt_concurrently:
| /*EMPTY*/ { $$ = false; }
;
+opt_usingindex:
+ USING INDEX { $$ = true; }
+ | /* EMPTY */ { $$ = false; }
+ ;
+
opt_drop_behavior:
CASCADE { $$ = DROP_CASCADE; }
| RESTRICT { $$ = DROP_RESTRICT; }
@@ -11979,38 +11984,82 @@ CreateConversionStmt:
/*****************************************************************************
*
* QUERY:
+ * REPACK [ (options) ] [ <qualified_name> [ <name_list> ] [ USING INDEX <index_name> ] ]
+ *
+ * obsolete variants:
* CLUSTER (options) [ <qualified_name> [ USING <index_name> ] ]
* CLUSTER [VERBOSE] [ <qualified_name> [ USING <index_name> ] ]
* CLUSTER [VERBOSE] <index_name> ON <qualified_name> (for pre-8.3)
*
*****************************************************************************/
-ClusterStmt:
- CLUSTER '(' utility_option_list ')' qualified_name cluster_index_specification
+RepackStmt:
+ REPACK opt_utility_option_list vacuum_relation USING INDEX name
{
- ClusterStmt *n = makeNode(ClusterStmt);
+ RepackStmt *n = makeNode(RepackStmt);
- n->relation = $5;
+ n->command = REPACK_COMMAND_REPACK;
+ n->relation = (VacuumRelation *) $3;
n->indexname = $6;
+ n->usingindex = true;
+ n->params = $2;
+ $$ = (Node *) n;
+ }
+ | REPACK opt_utility_option_list vacuum_relation opt_usingindex
+ {
+ RepackStmt *n = makeNode(RepackStmt);
+
+ n->command = REPACK_COMMAND_REPACK;
+ n->relation = (VacuumRelation *) $3;
+ n->indexname = NULL;
+ n->usingindex = $4;
+ n->params = $2;
+ $$ = (Node *) n;
+ }
+ | REPACK opt_utility_option_list opt_usingindex
+ {
+ RepackStmt *n = makeNode(RepackStmt);
+
+ n->command = REPACK_COMMAND_REPACK;
+ n->relation = NULL;
+ n->indexname = NULL;
+ n->usingindex = $3;
+ n->params = $2;
+ $$ = (Node *) n;
+ }
+ | CLUSTER '(' utility_option_list ')' qualified_name cluster_index_specification
+ {
+ RepackStmt *n = makeNode(RepackStmt);
+
+ n->command = REPACK_COMMAND_CLUSTER;
+ n->relation = makeNode(VacuumRelation);
+ n->relation->relation = $5;
+ n->indexname = $6;
+ n->usingindex = true;
n->params = $3;
$$ = (Node *) n;
}
| CLUSTER opt_utility_option_list
{
- ClusterStmt *n = makeNode(ClusterStmt);
+ RepackStmt *n = makeNode(RepackStmt);
+ n->command = REPACK_COMMAND_CLUSTER;
n->relation = NULL;
n->indexname = NULL;
+ n->usingindex = true;
n->params = $2;
$$ = (Node *) n;
}
/* unparenthesized VERBOSE kept for pre-14 compatibility */
| CLUSTER opt_verbose qualified_name cluster_index_specification
{
- ClusterStmt *n = makeNode(ClusterStmt);
+ RepackStmt *n = makeNode(RepackStmt);
- n->relation = $3;
+ n->command = REPACK_COMMAND_CLUSTER;
+ n->relation = makeNode(VacuumRelation);
+ n->relation->relation = $3;
n->indexname = $4;
+ n->usingindex = true;
if ($2)
n->params = list_make1(makeDefElem("verbose", NULL, @2));
$$ = (Node *) n;
@@ -12018,20 +12067,25 @@ ClusterStmt:
/* unparenthesized VERBOSE kept for pre-17 compatibility */
| CLUSTER VERBOSE
{
- ClusterStmt *n = makeNode(ClusterStmt);
+ RepackStmt *n = makeNode(RepackStmt);
+ n->command = REPACK_COMMAND_CLUSTER;
n->relation = NULL;
n->indexname = NULL;
+ n->usingindex = true;
n->params = list_make1(makeDefElem("verbose", NULL, @2));
$$ = (Node *) n;
}
/* kept for pre-8.3 compatibility */
| CLUSTER opt_verbose name ON qualified_name
{
- ClusterStmt *n = makeNode(ClusterStmt);
+ RepackStmt *n = makeNode(RepackStmt);
- n->relation = $5;
+ n->command = REPACK_COMMAND_CLUSTER;
+ n->relation = makeNode(VacuumRelation);
+ n->relation->relation = $5;
n->indexname = $3;
+ n->usingindex = true;
if ($2)
n->params = list_make1(makeDefElem("verbose", NULL, @2));
$$ = (Node *) n;
@@ -18069,6 +18123,7 @@ unreserved_keyword:
| RELATIVE_P
| RELEASE
| RENAME
+ | REPACK
| REPEATABLE
| REPLACE
| REPLICA
@@ -18704,6 +18759,7 @@ bare_label_keyword:
| RELATIVE_P
| RELEASE
| RENAME
+ | REPACK
| REPEATABLE
| REPLACE
| REPLICA
diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c
index d18a3a60a46..3e731dc8117 100644
--- a/src/backend/tcop/utility.c
+++ b/src/backend/tcop/utility.c
@@ -279,9 +279,9 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree)
return COMMAND_OK_IN_RECOVERY | COMMAND_OK_IN_READ_ONLY_TXN;
}
- case T_ClusterStmt:
case T_ReindexStmt:
case T_VacuumStmt:
+ case T_RepackStmt:
{
/*
* These commands write WAL, so they're not strictly
@@ -856,14 +856,14 @@ standard_ProcessUtility(PlannedStmt *pstmt,
ExecuteCallStmt(castNode(CallStmt, parsetree), params, isAtomicContext, dest);
break;
- case T_ClusterStmt:
- cluster(pstate, (ClusterStmt *) parsetree, isTopLevel);
- break;
-
case T_VacuumStmt:
ExecVacuum(pstate, (VacuumStmt *) parsetree, isTopLevel);
break;
+ case T_RepackStmt:
+ ExecRepack(pstate, (RepackStmt *) parsetree, isTopLevel);
+ break;
+
case T_ExplainStmt:
ExplainQuery(pstate, (ExplainStmt *) parsetree, params, dest);
break;
@@ -2864,10 +2864,6 @@ CreateCommandTag(Node *parsetree)
tag = CMDTAG_CALL;
break;
- case T_ClusterStmt:
- tag = CMDTAG_CLUSTER;
- break;
-
case T_VacuumStmt:
if (((VacuumStmt *) parsetree)->is_vacuumcmd)
tag = CMDTAG_VACUUM;
@@ -2875,6 +2871,13 @@ CreateCommandTag(Node *parsetree)
tag = CMDTAG_ANALYZE;
break;
+ case T_RepackStmt:
+ if (((RepackStmt *) parsetree)->command == REPACK_COMMAND_CLUSTER)
+ tag = CMDTAG_CLUSTER;
+ else
+ tag = CMDTAG_REPACK;
+ break;
+
case T_ExplainStmt:
tag = CMDTAG_EXPLAIN;
break;
@@ -3516,7 +3519,7 @@ GetCommandLogLevel(Node *parsetree)
lev = LOGSTMT_ALL;
break;
- case T_ClusterStmt:
+ case T_RepackStmt:
lev = LOGSTMT_DDL;
break;
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..fc86cbb3b88 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -289,6 +289,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS)
cmdtype = PROGRESS_COMMAND_ANALYZE;
else if (pg_strcasecmp(cmd, "CLUSTER") == 0)
cmdtype = PROGRESS_COMMAND_CLUSTER;
+ else if (pg_strcasecmp(cmd, "REPACK") == 0)
+ cmdtype = PROGRESS_COMMAND_REPACK;
else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0)
cmdtype = PROGRESS_COMMAND_CREATE_INDEX;
else if (pg_strcasecmp(cmd, "BASEBACKUP") == 0)
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 20d7a65c614..626d9f1c98b 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1267,7 +1267,7 @@ static const char *const sql_commands[] = {
"DELETE FROM", "DISCARD", "DO", "DROP", "END", "EXECUTE", "EXPLAIN",
"FETCH", "GRANT", "IMPORT FOREIGN SCHEMA", "INSERT INTO", "LISTEN", "LOAD", "LOCK",
"MERGE INTO", "MOVE", "NOTIFY", "PREPARE",
- "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE",
+ "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE", "REPACK",
"RESET", "REVOKE", "ROLLBACK",
"SAVEPOINT", "SECURITY LABEL", "SELECT", "SET", "SHOW", "START",
"TABLE", "TRUNCATE", "UNLISTEN", "UPDATE", "VACUUM", "VALUES",
@@ -5040,6 +5040,46 @@ match_previous_words(int pattern_id,
COMPLETE_WITH_QUERY(Query_for_list_of_tablespaces);
}
+/* REPACK */
+ else if (Matches("REPACK"))
+ COMPLETE_WITH_SCHEMA_QUERY_PLUS(Query_for_list_of_clusterables,
+ "(", "USING INDEX");
+ else if (Matches("REPACK", "(*)"))
+ COMPLETE_WITH_SCHEMA_QUERY_PLUS(Query_for_list_of_clusterables,
+ "USING INDEX");
+ else if (Matches("REPACK", MatchAnyExcept("(")))
+ COMPLETE_WITH("USING INDEX");
+ else if (Matches("REPACK", "(*)", MatchAnyExcept("(")))
+ COMPLETE_WITH("USING INDEX");
+ else if (Matches("REPACK", MatchAny, "USING", "INDEX") ||
+ Matches("REPACK", "(*)", MatchAny, "USING", "INDEX"))
+ {
+ set_completion_reference(prev3_wd);
+ COMPLETE_WITH_SCHEMA_QUERY(Query_for_index_of_table);
+ }
+ /*
+ * Complete ... [ (*) ] <sth> USING INDEX, with a list of indexes for
+ * <sth>.
+ */
+ else if (TailMatches(MatchAny, "USING", "INDEX"))
+ {
+ set_completion_reference(prev3_wd);
+ COMPLETE_WITH_SCHEMA_QUERY(Query_for_index_of_table);
+ }
+ else if (HeadMatches("REPACK", "(*") &&
+ !HeadMatches("REPACK", "(*)"))
+ {
+ /*
+ * This fires if we're in an unfinished parenthesized option list.
+ * get_previous_words treats a completed parenthesized option list as
+ * one word, so the above test is correct.
+ */
+ if (ends_with(prev_wd, '(') || ends_with(prev_wd, ','))
+ COMPLETE_WITH("ANALYZE", "VERBOSE");
+ else if (TailMatches("ANALYZE", "VERBOSE"))
+ COMPLETE_WITH("ON", "OFF");
+ }
+
/* SECURITY LABEL */
else if (Matches("SECURITY"))
COMPLETE_WITH("LABEL");
diff --git a/src/bin/scripts/Makefile b/src/bin/scripts/Makefile
index 019ca06455d..f0c1bd4175c 100644
--- a/src/bin/scripts/Makefile
+++ b/src/bin/scripts/Makefile
@@ -16,7 +16,7 @@ subdir = src/bin/scripts
top_builddir = ../../..
include $(top_builddir)/src/Makefile.global
-PROGRAMS = createdb createuser dropdb dropuser clusterdb vacuumdb reindexdb pg_isready
+PROGRAMS = createdb createuser dropdb dropuser clusterdb vacuumdb reindexdb pg_isready pg_repackdb
override CPPFLAGS := -I$(libpq_srcdir) $(CPPFLAGS)
LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils $(libpq_pgport)
@@ -31,6 +31,7 @@ clusterdb: clusterdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport su
vacuumdb: vacuumdb.o vacuuming.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils
reindexdb: reindexdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils
pg_isready: pg_isready.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils
+pg_repackdb: pg_repackdb.o vacuuming.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils
install: all installdirs
$(INSTALL_PROGRAM) createdb$(X) '$(DESTDIR)$(bindir)'/createdb$(X)
@@ -41,6 +42,7 @@ install: all installdirs
$(INSTALL_PROGRAM) vacuumdb$(X) '$(DESTDIR)$(bindir)'/vacuumdb$(X)
$(INSTALL_PROGRAM) reindexdb$(X) '$(DESTDIR)$(bindir)'/reindexdb$(X)
$(INSTALL_PROGRAM) pg_isready$(X) '$(DESTDIR)$(bindir)'/pg_isready$(X)
+ $(INSTALL_PROGRAM) pg_repackdb$(X) '$(DESTDIR)$(bindir)'/pg_repackdb$(X)
installdirs:
$(MKDIR_P) '$(DESTDIR)$(bindir)'
diff --git a/src/bin/scripts/meson.build b/src/bin/scripts/meson.build
index a4fed59d1c9..be573cae682 100644
--- a/src/bin/scripts/meson.build
+++ b/src/bin/scripts/meson.build
@@ -42,6 +42,7 @@ vacuuming_common = static_library('libvacuuming_common',
binaries = [
'vacuumdb',
+ 'pg_repackdb',
]
foreach binary : binaries
binary_sources = files('@0@.c'.format(binary))
@@ -80,6 +81,7 @@ tests += {
't/100_vacuumdb.pl',
't/101_vacuumdb_all.pl',
't/102_vacuumdb_stages.pl',
+ 't/103_repackdb.pl',
't/200_connstr.pl',
],
},
diff --git a/src/bin/scripts/pg_repackdb.c b/src/bin/scripts/pg_repackdb.c
new file mode 100644
index 00000000000..2765d1e97b8
--- /dev/null
+++ b/src/bin/scripts/pg_repackdb.c
@@ -0,0 +1,240 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_repackdb
+ * An utility to run REPACK
+ *
+ * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * FIXME: this is missing a way to specify the index to use to repack one
+ * table, or whether to pass a WITH INDEX clause when multiple tables are
+ * used. Something like --index[=indexname]. Adding that bleeds into
+ * vacuuming.c as well.
+ *
+ * src/bin/scripts/pg_repackdb.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <limits.h>
+
+#include "common.h"
+#include "common/logging.h"
+#include "fe_utils/option_utils.h"
+#include "vacuuming.h"
+
+static void help(const char *progname);
+static void check_objfilter(bits32 objfilter);
+
+int
+main(int argc, char *argv[])
+{
+ static struct option long_options[] = {
+ {"host", required_argument, NULL, 'h'},
+ {"port", required_argument, NULL, 'p'},
+ {"username", required_argument, NULL, 'U'},
+ {"no-password", no_argument, NULL, 'w'},
+ {"password", no_argument, NULL, 'W'},
+ {"echo", no_argument, NULL, 'e'},
+ {"quiet", no_argument, NULL, 'q'},
+ {"dbname", required_argument, NULL, 'd'},
+ {"analyze", no_argument, NULL, 'z'},
+ {"all", no_argument, NULL, 'a'},
+ /* XXX this could be 'i', but optional_arg is messy */
+ {"index", optional_argument, NULL, 1},
+ {"table", required_argument, NULL, 't'},
+ {"verbose", no_argument, NULL, 'v'},
+ {"jobs", required_argument, NULL, 'j'},
+ {"schema", required_argument, NULL, 'n'},
+ {"exclude-schema", required_argument, NULL, 'N'},
+ {"maintenance-db", required_argument, NULL, 2},
+ {NULL, 0, NULL, 0}
+ };
+
+ const char *progname;
+ int optindex;
+ int c;
+ const char *dbname = NULL;
+ const char *maintenance_db = NULL;
+ ConnParams cparams;
+ vacuumingOptions vacopts;
+ SimpleStringList objects = {NULL, NULL};
+ int concurrentCons = 1;
+ int tbl_count = 0;
+ int ret;
+
+ /* initialize options */
+ memset(&vacopts, 0, sizeof(vacopts));
+ vacopts.mode = MODE_REPACK;
+
+ /* the same for connection parameters */
+ memset(&cparams, 0, sizeof(cparams));
+ cparams.prompt_password = TRI_DEFAULT;
+
+ pg_logging_init(argv[0]);
+ progname = get_progname(argv[0]);
+ set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pgscripts"));
+
+ handle_help_version_opts(argc, argv, progname, help);
+
+ while ((c = getopt_long(argc, argv, "ad:eh:j:n:N:p:qt:U:vwWz",
+ long_options, &optindex)) != -1)
+ {
+ switch (c)
+ {
+ case 'a':
+ vacopts.objfilter |= OBJFILTER_ALL_DBS;
+ break;
+ case 'd':
+ vacopts.objfilter |= OBJFILTER_DATABASE;
+ dbname = pg_strdup(optarg);
+ break;
+ case 'e':
+ vacopts.echo = true;
+ break;
+ case 'h':
+ cparams.pghost = pg_strdup(optarg);
+ break;
+ case 'j':
+ if (!option_parse_int(optarg, "-j/--jobs", 1, INT_MAX,
+ &concurrentCons))
+ exit(1);
+ break;
+ case 'n':
+ vacopts.objfilter |= OBJFILTER_SCHEMA;
+ simple_string_list_append(&objects, optarg);
+ break;
+ case 'N':
+ vacopts.objfilter |= OBJFILTER_SCHEMA_EXCLUDE;
+ simple_string_list_append(&objects, optarg);
+ break;
+ case 'p':
+ cparams.pgport = pg_strdup(optarg);
+ break;
+ case 'q':
+ vacopts.quiet = true;
+ break;
+ case 't':
+ vacopts.objfilter |= OBJFILTER_TABLE;
+ simple_string_list_append(&objects, optarg);
+ tbl_count++;
+ break;
+ case 'U':
+ cparams.pguser = pg_strdup(optarg);
+ break;
+ case 'v':
+ vacopts.verbose = true;
+ break;
+ case 'w':
+ cparams.prompt_password = TRI_NO;
+ break;
+ case 'W':
+ cparams.prompt_password = TRI_YES;
+ break;
+ case 'z':
+ vacopts.and_analyze = true;
+ break;
+ case 1:
+ vacopts.using_index = true;
+ if (optarg)
+ vacopts.indexname = pg_strdup(optarg);
+ else
+ vacopts.indexname = NULL;
+ break;
+ case 2:
+ maintenance_db = pg_strdup(optarg);
+ break;
+ default:
+ /* getopt_long already emitted a complaint */
+ pg_log_error_hint("Try \"%s --help\" for more information.", progname);
+ exit(1);
+ }
+ }
+
+ /*
+ * Non-option argument specifies database name as long as it wasn't
+ * already specified with -d / --dbname
+ */
+ if (optind < argc && dbname == NULL)
+ {
+ vacopts.objfilter |= OBJFILTER_DATABASE;
+ dbname = argv[optind];
+ optind++;
+ }
+
+ if (optind < argc)
+ {
+ pg_log_error("too many command-line arguments (first is \"%s\")",
+ argv[optind]);
+ pg_log_error_hint("Try \"%s --help\" for more information.", progname);
+ exit(1);
+ }
+
+ /*
+ * Validate the combination of filters specified in the command-line
+ * options.
+ */
+ check_objfilter(vacopts.objfilter);
+
+ ret = vacuuming_main(&cparams, dbname, maintenance_db, &vacopts,
+ &objects, tbl_count, concurrentCons,
+ progname);
+ exit(ret);
+}
+
+/*
+ * Verify that the filters used at command line are compatible.
+ */
+void
+check_objfilter(bits32 objfilter)
+{
+ if ((objfilter & OBJFILTER_ALL_DBS) &&
+ (objfilter & OBJFILTER_DATABASE))
+ pg_fatal("cannot repack all databases and a specific one at the same time");
+
+ if ((objfilter & OBJFILTER_TABLE) &&
+ (objfilter & OBJFILTER_SCHEMA))
+ pg_fatal("cannot repack all tables in schema(s) and specific table(s) at the same time");
+
+ if ((objfilter & OBJFILTER_TABLE) &&
+ (objfilter & OBJFILTER_SCHEMA_EXCLUDE))
+ pg_fatal("cannot repack specific table(s) and exclude schema(s) at the same time");
+
+ if ((objfilter & OBJFILTER_SCHEMA) &&
+ (objfilter & OBJFILTER_SCHEMA_EXCLUDE))
+ pg_fatal("cannot repack all tables in schema(s) and exclude schema(s) at the same time");
+}
+
+static void
+help(const char *progname)
+{
+ printf(_("%s repacks a PostgreSQL database.\n\n"), progname);
+ printf(_("Usage:\n"));
+ printf(_(" %s [OPTION]... [DBNAME]\n"), progname);
+ printf(_("\nOptions:\n"));
+ printf(_(" -a, --all repack all databases\n"));
+ printf(_(" -d, --dbname=DBNAME database to repack\n"));
+ printf(_(" -e, --echo show the commands being sent to the server\n"));
+ printf(_(" --index[=INDEX] repack following an index\n"));
+ printf(_(" -j, --jobs=NUM use this many concurrent connections to repack\n"));
+ printf(_(" -n, --schema=SCHEMA repack tables in the specified schema(s) only\n"));
+ printf(_(" -N, --exclude-schema=SCHEMA do not repack tables in the specified schema(s)\n"));
+ printf(_(" -q, --quiet don't write any messages\n"));
+ printf(_(" -t, --table='TABLE[(COLUMNS)]' repack specific table(s) only\n"));
+ printf(_(" -v, --verbose write a lot of output\n"));
+ printf(_(" -V, --version output version information, then exit\n"));
+ printf(_(" -z, --analyze update optimizer statistics\n"));
+ printf(_(" -?, --help show this help, then exit\n"));
+ printf(_("\nConnection options:\n"));
+ printf(_(" -h, --host=HOSTNAME database server host or socket directory\n"));
+ printf(_(" -p, --port=PORT database server port\n"));
+ printf(_(" -U, --username=USERNAME user name to connect as\n"));
+ printf(_(" -w, --no-password never prompt for password\n"));
+ printf(_(" -W, --password force password prompt\n"));
+ printf(_(" --maintenance-db=DBNAME alternate maintenance database\n"));
+ printf(_("\nRead the description of the SQL command REPACK for details.\n"));
+ printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
+ printf(_("%s home page: <%s>\n"), PACKAGE_NAME, PACKAGE_URL);
+}
diff --git a/src/bin/scripts/t/103_repackdb.pl b/src/bin/scripts/t/103_repackdb.pl
new file mode 100644
index 00000000000..cadce9b837c
--- /dev/null
+++ b/src/bin/scripts/t/103_repackdb.pl
@@ -0,0 +1,47 @@
+# Copyright (c) 2021-2025, PostgreSQL Global Development Group
+
+use strict;
+use warnings FATAL => 'all';
+
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+program_help_ok('pg_repackdb');
+program_version_ok('pg_repackdb');
+program_options_handling_ok('pg_repackdb');
+
+my $node = PostgreSQL::Test::Cluster->new('main');
+$node->init;
+$node->start;
+
+$node->issues_sql_like(
+ [ 'pg_repackdb', 'postgres', '-t', 'pg_class'],
+ qr/statement: REPACK.*pg_class;/,
+ 'pg_repackdb processes a single table');
+
+$node->safe_psql('postgres', 'CREATE USER testusr;
+ GRANT CREATE ON SCHEMA public TO testusr');
+$node->safe_psql('postgres',
+ 'CREATE TABLE cluster_1 (a int primary key);
+ ALTER TABLE cluster_1 CLUSTER ON cluster_1_pkey;
+ CREATE TABLE cluster_2 (a int unique);
+ ALTER TABLE cluster_2 CLUSTER ON cluster_2_a_key;',
+ extra_params => ['-U' => 'testusr']);
+
+$node->issues_sql_like(
+ [ 'pg_repackdb', 'postgres', '-U', 'testusr' ],
+ qr/statement: REPACK.*;/,
+ 'SQL REPACK run');
+
+$node->issues_sql_like(
+ [ 'pg_repackdb', 'postgres', '--index'],
+ qr/statement: REPACK.*cluster_1 USING INDEX.*statement: REPACK.*cluster_2 USING INDEX/ms,
+ 'pg_repackdb --index chooses multiple tables');
+
+$node->issues_sql_like(
+ [ 'pg_repackdb', 'postgres', '--analyze', '-t', 'cluster_1'],
+ qr/statement: REPACK \(ANALYZE\) public.cluster_1/,
+ 'pg_repackdb --analyze works');
+
+done_testing();
diff --git a/src/bin/scripts/vacuuming.c b/src/bin/scripts/vacuuming.c
index 5d2d8a64961..2e3d6d2ad73 100644
--- a/src/bin/scripts/vacuuming.c
+++ b/src/bin/scripts/vacuuming.c
@@ -1,6 +1,6 @@
/*-------------------------------------------------------------------------
* vacuuming.c
- * Helper routines for vacuumdb
+ * Helper routines for vacuumdb and pg_repackdb
*
* Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
@@ -194,6 +194,14 @@ vacuum_one_database(ConnParams *cparams,
conn = connectDatabase(cparams, progname, vacopts->echo, false, true);
+ if (vacopts->mode == MODE_REPACK && PQserverVersion(conn) < 190000)
+ {
+ /* XXX arguably, here we should use VACUUM FULL instead of failing */
+ PQfinish(conn);
+ pg_fatal("cannot use the \"%s\" command on server versions older than PostgreSQL %s",
+ "REPACK", "19");
+ }
+
if (vacopts->disable_page_skipping && PQserverVersion(conn) < 90600)
{
PQfinish(conn);
@@ -286,9 +294,18 @@ vacuum_one_database(ConnParams *cparams,
if (vacopts->mode == MODE_ANALYZE_IN_STAGES)
printf(_("%s: processing database \"%s\": %s\n"),
progname, PQdb(conn), _(stage_messages[stage]));
- else
+ else if (vacopts->mode == MODE_ANALYZE)
+ printf(_("%s: analyzing database \"%s\"\n"),
+ progname, PQdb(conn));
+ else if (vacopts->mode == MODE_VACUUM)
printf(_("%s: vacuuming database \"%s\"\n"),
progname, PQdb(conn));
+ else
+ {
+ Assert(vacopts->mode == MODE_REPACK);
+ printf(_("%s: repacking database \"%s\"\n"),
+ progname, PQdb(conn));
+ }
fflush(stdout);
}
@@ -640,6 +657,35 @@ retrieve_objects(PGconn *conn, vacuumingOptions *vacopts,
" AND listed_objects.object_oid IS NOT NULL\n");
}
+ /*
+ * In REPACK mode, if the 'using_index' option was given but no index
+ * name, filter only tables that have an index with indisclustered set.
+ * (If an index name is given, we trust the user to pass a reasonable list
+ * of tables.)
+ *
+ * XXX it may be worth printing an error if an index name is given with no
+ * list of tables.
+ */
+ if (vacopts->mode == MODE_REPACK &&
+ vacopts->using_index && !vacopts->indexname)
+ {
+ appendPQExpBufferStr(&catalog_query,
+ " AND EXISTS (SELECT 1 FROM pg_catalog.pg_index\n"
+ " WHERE indrelid = c.oid AND indisclustered)\n");
+ }
+
+ /*
+ * In REPACK mode, only consider the tables that the current user has
+ * MAINTAIN privileges on. XXX maybe we should do this in all cases, not
+ * just REPACK. The vacuumdb output is too noisy for no reason.
+ */
+ if (vacopts->mode == MODE_REPACK)
+ {
+ appendPQExpBufferStr(&catalog_query,
+ " AND pg_catalog.has_table_privilege(current_user, "
+ "c.oid, 'MAINTAIN')\n");
+ }
+
/*
* If no tables were listed, filter for the relevant relation types. If
* tables were given via --table, don't bother filtering by relation type.
@@ -878,8 +924,10 @@ prepare_vacuum_command(PGconn *conn, PQExpBuffer sql,
if (vacopts->verbose)
appendPQExpBufferStr(sql, " VERBOSE");
}
+
+ appendPQExpBuffer(sql, " %s", table);
}
- else
+ else if (vacopts->mode == MODE_VACUUM)
{
appendPQExpBufferStr(sql, "VACUUM");
@@ -993,9 +1041,39 @@ prepare_vacuum_command(PGconn *conn, PQExpBuffer sql,
if (vacopts->and_analyze)
appendPQExpBufferStr(sql, " ANALYZE");
}
+
+ appendPQExpBuffer(sql, " %s", table);
}
+ else if (vacopts->mode == MODE_REPACK)
+ {
+ appendPQExpBufferStr(sql, "REPACK");
- appendPQExpBuffer(sql, " %s;", table);
+ if (vacopts->verbose)
+ {
+ appendPQExpBuffer(sql, "%sVERBOSE", sep);
+ sep = comma;
+ }
+ if (vacopts->and_analyze)
+ {
+ appendPQExpBuffer(sql, "%sANALYZE", sep);
+ sep = comma;
+ }
+
+ if (sep != paren)
+ appendPQExpBufferChar(sql, ')');
+
+ appendPQExpBuffer(sql, " %s", table);
+
+ if (vacopts->using_index)
+ {
+ appendPQExpBuffer(sql, " USING INDEX");
+ if (vacopts->indexname)
+ appendPQExpBuffer(sql, " %s", fmtIdEnc(vacopts->indexname,
+ PQclientEncoding(conn)));
+ }
+ }
+
+ appendPQExpBufferChar(sql, ';');
}
/*
@@ -1024,13 +1102,21 @@ run_vacuum_command(ParallelSlot *free_slot, vacuumingOptions *vacopts,
{
if (table)
{
- pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s",
- table, PQdb(conn), PQerrorMessage(conn));
+ if (vacopts->mode == MODE_VACUUM)
+ pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s",
+ table, PQdb(conn), PQerrorMessage(conn));
+ else
+ pg_log_error("repacking of table \"%s\" in database \"%s\" failed: %s",
+ table, PQdb(conn), PQerrorMessage(conn));
}
else
{
- pg_log_error("vacuuming of database \"%s\" failed: %s",
- PQdb(conn), PQerrorMessage(conn));
+ if (vacopts->mode == MODE_VACUUM)
+ pg_log_error("vacuuming of database \"%s\" failed: %s",
+ PQdb(conn), PQerrorMessage(conn));
+ else
+ pg_log_error("repacking of database \"%s\" failed: %s",
+ PQdb(conn), PQerrorMessage(conn));
}
}
}
diff --git a/src/bin/scripts/vacuuming.h b/src/bin/scripts/vacuuming.h
index 586b6caa3d6..dba6ac6f6e0 100644
--- a/src/bin/scripts/vacuuming.h
+++ b/src/bin/scripts/vacuuming.h
@@ -20,6 +20,7 @@
typedef enum
{
MODE_VACUUM,
+ MODE_REPACK,
MODE_ANALYZE,
MODE_ANALYZE_IN_STAGES
} RunMode;
@@ -37,6 +38,8 @@ typedef struct vacuumingOptions
bool and_analyze;
bool full;
bool freeze;
+ bool using_index;
+ char *indexname;
bool disable_page_skipping;
bool skip_locked;
int min_xid_age;
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 60088a64cbb..652542e8e65 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -24,6 +24,7 @@
#define CLUOPT_RECHECK 0x02 /* recheck relation state */
#define CLUOPT_RECHECK_ISCLUSTERED 0x04 /* recheck relation state for
* indisclustered */
+#define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */
/* options for CLUSTER */
typedef struct ClusterParams
@@ -31,8 +32,11 @@ typedef struct ClusterParams
bits32 options; /* bitmask of CLUOPT_* */
} ClusterParams;
-extern void cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel);
-extern void cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params);
+
+extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
+
+extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid indexOid,
+ ClusterParams *params);
extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid,
LOCKMODE lockmode);
extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_internal);
diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h
index 9dc63a5a5bd..8d68bcbef95 100644
--- a/src/include/commands/progress.h
+++ b/src/include/commands/progress.h
@@ -73,28 +73,34 @@
#define PROGRESS_ANALYZE_STARTED_BY_MANUAL 1
#define PROGRESS_ANALYZE_STARTED_BY_AUTOVACUUM 2
-/* Progress parameters for cluster */
-#define PROGRESS_CLUSTER_COMMAND 0
-#define PROGRESS_CLUSTER_PHASE 1
-#define PROGRESS_CLUSTER_INDEX_RELID 2
-#define PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED 3
-#define PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN 4
-#define PROGRESS_CLUSTER_TOTAL_HEAP_BLKS 5
-#define PROGRESS_CLUSTER_HEAP_BLKS_SCANNED 6
-#define PROGRESS_CLUSTER_INDEX_REBUILD_COUNT 7
-
-/* Phases of cluster (as advertised via PROGRESS_CLUSTER_PHASE) */
-#define PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP 1
-#define PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP 2
-#define PROGRESS_CLUSTER_PHASE_SORT_TUPLES 3
-#define PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP 4
-#define PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES 5
-#define PROGRESS_CLUSTER_PHASE_REBUILD_INDEX 6
-#define PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP 7
-
-/* Commands of PROGRESS_CLUSTER */
-#define PROGRESS_CLUSTER_COMMAND_CLUSTER 1
-#define PROGRESS_CLUSTER_COMMAND_VACUUM_FULL 2
+/*
+ * Progress parameters for REPACK.
+ *
+ * Values for PROGRESS_REPACK_COMMAND are defined as in RepackCommand.
+ *
+ * Note: Since REPACK shares code with CLUSTER, these values are also
+ * used by CLUSTER. (CLUSTER is now deprecated, so it makes little sense to
+ * introduce a separate set of constants.)
+ */
+#define PROGRESS_REPACK_COMMAND 0
+#define PROGRESS_REPACK_PHASE 1
+#define PROGRESS_REPACK_INDEX_RELID 2
+#define PROGRESS_REPACK_HEAP_TUPLES_SCANNED 3
+#define PROGRESS_REPACK_HEAP_TUPLES_WRITTEN 4
+#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 5
+#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 6
+#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 7
+
+/*
+ * Phases of repack (as advertised via PROGRESS_REPACK_PHASE).
+ */
+#define PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP 1
+#define PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP 2
+#define PROGRESS_REPACK_PHASE_SORT_TUPLES 3
+#define PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP 4
+#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 5
+#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 6
+#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 7
/* Progress parameters for CREATE INDEX */
/* 3, 4 and 5 reserved for "waitfor" metrics */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index d14294a4ece..94892042b8d 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3951,18 +3951,6 @@ typedef struct AlterSystemStmt
VariableSetStmt *setstmt; /* SET subcommand */
} AlterSystemStmt;
-/* ----------------------
- * Cluster Statement (support pbrown's cluster index implementation)
- * ----------------------
- */
-typedef struct ClusterStmt
-{
- NodeTag type;
- RangeVar *relation; /* relation being indexed, or NULL if all */
- char *indexname; /* original index defined */
- List *params; /* list of DefElem nodes */
-} ClusterStmt;
-
/* ----------------------
* Vacuum and Analyze Statements
*
@@ -3975,7 +3963,7 @@ typedef struct VacuumStmt
NodeTag type;
List *options; /* list of DefElem nodes */
List *rels; /* list of VacuumRelation, or NIL for all */
- bool is_vacuumcmd; /* true for VACUUM, false for ANALYZE */
+ bool is_vacuumcmd; /* true for VACUUM, false otherwise */
} VacuumStmt;
/*
@@ -3993,6 +3981,27 @@ typedef struct VacuumRelation
List *va_cols; /* list of column names, or NIL for all */
} VacuumRelation;
+/* ----------------------
+ * Repack Statement
+ * ----------------------
+ */
+typedef enum RepackCommand
+{
+ REPACK_COMMAND_CLUSTER = 1,
+ REPACK_COMMAND_REPACK,
+ REPACK_COMMAND_VACUUMFULL,
+} RepackCommand;
+
+typedef struct RepackStmt
+{
+ NodeTag type;
+ RepackCommand command; /* type of command being run */
+ VacuumRelation *relation; /* relation being repacked */
+ char *indexname; /* order tuples by this index */
+ bool usingindex; /* whether USING INDEX is specified */
+ List *params; /* list of DefElem nodes */
+} RepackStmt;
+
/* ----------------------
* Explain Statement
*
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index 5d4fe27ef96..f1a1d5e7a80 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -376,6 +376,7 @@ PG_KEYWORD("reindex", REINDEX, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("relative", RELATIVE_P, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("release", RELEASE, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("rename", RENAME, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("repack", REPACK, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("repeatable", REPEATABLE, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("replace", REPLACE, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("replica", REPLICA, UNRESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h
index c4606d65043..66690f1134a 100644
--- a/src/include/tcop/cmdtaglist.h
+++ b/src/include/tcop/cmdtaglist.h
@@ -196,6 +196,7 @@ PG_CMDTAG(CMDTAG_REASSIGN_OWNED, "REASSIGN OWNED", false, false, false)
PG_CMDTAG(CMDTAG_REFRESH_MATERIALIZED_VIEW, "REFRESH MATERIALIZED VIEW", true, false, false)
PG_CMDTAG(CMDTAG_REINDEX, "REINDEX", true, false, false)
PG_CMDTAG(CMDTAG_RELEASE, "RELEASE", false, false, false)
+PG_CMDTAG(CMDTAG_REPACK, "REPACK", false, false, false)
PG_CMDTAG(CMDTAG_RESET, "RESET", false, false, false)
PG_CMDTAG(CMDTAG_REVOKE, "REVOKE", true, false, false)
PG_CMDTAG(CMDTAG_REVOKE_ROLE, "REVOKE ROLE", false, false, false)
diff --git a/src/include/utils/backend_progress.h b/src/include/utils/backend_progress.h
index dda813ab407..e69e366dcdc 100644
--- a/src/include/utils/backend_progress.h
+++ b/src/include/utils/backend_progress.h
@@ -28,6 +28,7 @@ typedef enum ProgressCommandType
PROGRESS_COMMAND_CREATE_INDEX,
PROGRESS_COMMAND_BASEBACKUP,
PROGRESS_COMMAND_COPY,
+ PROGRESS_COMMAND_REPACK,
} ProgressCommandType;
#define PGSTAT_NUM_PROGRESS_PARAM 20
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index 4d40a6809ab..277854418fa 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -495,6 +495,43 @@ ALTER TABLE clstrpart SET WITHOUT CLUSTER;
ERROR: cannot mark index clustered in partitioned table
ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
ERROR: cannot mark index clustered in partitioned table
+-- Check that REPACK sets new relfilenodes: it should process exactly the same
+-- tables as CLUSTER did.
+DROP TABLE old_cluster_info;
+DROP TABLE new_cluster_info;
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+REPACK clstrpart USING INDEX clstrpart_idx;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+ relname | level | relkind | ?column?
+-------------+-------+---------+----------
+ clstrpart | 0 | p | t
+ clstrpart1 | 1 | p | t
+ clstrpart11 | 2 | r | f
+ clstrpart12 | 2 | p | t
+ clstrpart2 | 1 | r | f
+ clstrpart3 | 1 | p | t
+ clstrpart33 | 2 | r | f
+(7 rows)
+
+-- And finally the same for REPACK w/o index.
+DROP TABLE old_cluster_info;
+DROP TABLE new_cluster_info;
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+REPACK clstrpart;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+ relname | level | relkind | ?column?
+-------------+-------+---------+----------
+ clstrpart | 0 | p | t
+ clstrpart1 | 1 | p | t
+ clstrpart11 | 2 | r | f
+ clstrpart12 | 2 | p | t
+ clstrpart2 | 1 | r | f
+ clstrpart3 | 1 | p | t
+ clstrpart33 | 2 | r | f
+(7 rows)
+
DROP TABLE clstrpart;
-- Ownership of partitions is checked
CREATE TABLE ptnowner(i int unique) PARTITION BY LIST (i);
@@ -513,7 +550,7 @@ CREATE TEMP TABLE ptnowner_oldnodes AS
JOIN pg_class AS c ON c.oid=tree.relid;
SET SESSION AUTHORIZATION regress_ptnowner;
CLUSTER ptnowner USING ptnowner_i_idx;
-WARNING: permission denied to cluster "ptnowner2", skipping it
+WARNING: permission denied to execute CLUSTER on "ptnowner2", skipping it
RESET SESSION AUTHORIZATION;
SELECT a.relname, a.relfilenode=b.relfilenode FROM pg_class a
JOIN ptnowner_oldnodes b USING (oid) ORDER BY a.relname COLLATE "C";
@@ -665,6 +702,101 @@ SELECT * FROM clstr_expression WHERE -a = -3 ORDER BY -a, b;
(4 rows)
COMMIT;
+----------------------------------------------------------------------
+--
+-- REPACK
+--
+----------------------------------------------------------------------
+-- REPACK handles individual tables identically to CLUSTER, but it's worth
+-- checking if it handles table hierarchies identically as well.
+REPACK clstr_tst USING INDEX clstr_tst_c;
+-- Verify that inheritance link still works
+INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2');
+SELECT a,b,c,substring(d for 30), length(d) from clstr_tst;
+ a | b | c | substring | length
+----+-----+------------------+--------------------------------+--------
+ 10 | 14 | catorce | |
+ 18 | 5 | cinco | |
+ 9 | 4 | cuatro | |
+ 26 | 19 | diecinueve | |
+ 12 | 18 | dieciocho | |
+ 30 | 16 | dieciseis | |
+ 24 | 17 | diecisiete | |
+ 2 | 10 | diez | |
+ 23 | 12 | doce | |
+ 11 | 2 | dos | |
+ 25 | 9 | nueve | |
+ 31 | 8 | ocho | |
+ 1 | 11 | once | |
+ 28 | 15 | quince | |
+ 32 | 6 | seis | xyzzyxyzzyxyzzyxyzzyxyzzyxyzzy | 500000
+ 29 | 7 | siete | |
+ 15 | 13 | trece | |
+ 22 | 30 | treinta | |
+ 17 | 32 | treinta y dos | |
+ 3 | 31 | treinta y uno | |
+ 5 | 3 | tres | |
+ 20 | 1 | uno | |
+ 6 | 20 | veinte | |
+ 14 | 25 | veinticinco | |
+ 21 | 24 | veinticuatro | |
+ 4 | 22 | veintidos | |
+ 19 | 29 | veintinueve | |
+ 16 | 28 | veintiocho | |
+ 27 | 26 | veintiseis | |
+ 13 | 27 | veintisiete | |
+ 7 | 23 | veintitres | |
+ 8 | 21 | veintiuno | |
+ 0 | 100 | in child table | |
+ 0 | 100 | in child table 2 | |
+(34 rows)
+
+-- Verify that foreign key link still works
+INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail');
+ERROR: insert or update on table "clstr_tst" violates foreign key constraint "clstr_tst_con"
+DETAIL: Key (b)=(1111) is not present in table "clstr_tst_s".
+SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass
+ORDER BY 1;
+ conname
+----------------------
+ clstr_tst_a_not_null
+ clstr_tst_con
+ clstr_tst_pkey
+(3 rows)
+
+-- Verify partial analyze works
+REPACK (ANALYZE) clstr_tst (a);
+REPACK (ANALYZE) clstr_tst;
+REPACK (VERBOSE) clstr_tst (a);
+ERROR: ANALYZE option must be specified when a column list is provided
+-- REPACK w/o argument performs no ordering, so we can only check which tables
+-- have the relfilenode changed.
+RESET SESSION AUTHORIZATION;
+CREATE TEMP TABLE relnodes_old AS
+(SELECT relname, relfilenode
+FROM pg_class
+WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3'));
+SET SESSION AUTHORIZATION regress_clstr_user;
+SET client_min_messages = ERROR; -- order of "skipping" warnings may vary
+REPACK;
+RESET client_min_messages;
+RESET SESSION AUTHORIZATION;
+CREATE TEMP TABLE relnodes_new AS
+(SELECT relname, relfilenode
+FROM pg_class
+WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3'));
+-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been
+-- processed because there is nothing like clustering index here.
+SELECT o.relname FROM relnodes_old o
+JOIN relnodes_new n ON o.relname = n.relname
+WHERE o.relfilenode <> n.relfilenode
+ORDER BY o.relname;
+ relname
+---------
+ clstr_1
+ clstr_3
+(2 rows)
+
-- clean up
DROP TABLE clustertest;
DROP TABLE clstr_1;
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 4286c266e17..eb90fd3de5f 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -2000,34 +2000,23 @@ pg_stat_progress_basebackup| SELECT pid,
ELSE NULL::text
END AS backup_type
FROM pg_stat_get_progress_info('BASEBACKUP'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20);
-pg_stat_progress_cluster| SELECT s.pid,
- s.datid,
- d.datname,
- s.relid,
- CASE s.param1
- WHEN 1 THEN 'CLUSTER'::text
- WHEN 2 THEN 'VACUUM FULL'::text
- ELSE NULL::text
+pg_stat_progress_cluster| SELECT pid,
+ datid,
+ datname,
+ relid,
+ CASE
+ WHEN (command = ANY (ARRAY['CLUSTER'::text, 'VACUUM FULL'::text])) THEN command
+ WHEN (repack_index_relid = (0)::oid) THEN 'VACUUM FULL'::text
+ ELSE 'CLUSTER'::text
END AS command,
- CASE s.param2
- WHEN 0 THEN 'initializing'::text
- WHEN 1 THEN 'seq scanning heap'::text
- WHEN 2 THEN 'index scanning heap'::text
- WHEN 3 THEN 'sorting tuples'::text
- WHEN 4 THEN 'writing new heap'::text
- WHEN 5 THEN 'swapping relation files'::text
- WHEN 6 THEN 'rebuilding index'::text
- WHEN 7 THEN 'performing final cleanup'::text
- ELSE NULL::text
- END AS phase,
- (s.param3)::oid AS cluster_index_relid,
- s.param4 AS heap_tuples_scanned,
- s.param5 AS heap_tuples_written,
- s.param6 AS heap_blks_total,
- s.param7 AS heap_blks_scanned,
- s.param8 AS index_rebuild_count
- FROM (pg_stat_get_progress_info('CLUSTER'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
- LEFT JOIN pg_database d ON ((s.datid = d.oid)));
+ phase,
+ repack_index_relid AS cluster_index_relid,
+ heap_tuples_scanned,
+ heap_tuples_written,
+ heap_blks_total,
+ heap_blks_scanned,
+ index_rebuild_count
+ FROM pg_stat_progress_repack;
pg_stat_progress_copy| SELECT s.pid,
s.datid,
d.datname,
@@ -2087,6 +2076,35 @@ pg_stat_progress_create_index| SELECT s.pid,
s.param15 AS partitions_done
FROM (pg_stat_get_progress_info('CREATE INDEX'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
LEFT JOIN pg_database d ON ((s.datid = d.oid)));
+pg_stat_progress_repack| SELECT s.pid,
+ s.datid,
+ d.datname,
+ s.relid,
+ CASE s.param1
+ WHEN 1 THEN 'CLUSTER'::text
+ WHEN 2 THEN 'REPACK'::text
+ WHEN 3 THEN 'VACUUM FULL'::text
+ ELSE NULL::text
+ END AS command,
+ CASE s.param2
+ WHEN 0 THEN 'initializing'::text
+ WHEN 1 THEN 'seq scanning heap'::text
+ WHEN 2 THEN 'index scanning heap'::text
+ WHEN 3 THEN 'sorting tuples'::text
+ WHEN 4 THEN 'writing new heap'::text
+ WHEN 5 THEN 'swapping relation files'::text
+ WHEN 6 THEN 'rebuilding index'::text
+ WHEN 7 THEN 'performing final cleanup'::text
+ ELSE NULL::text
+ END AS phase,
+ (s.param3)::oid AS repack_index_relid,
+ s.param4 AS heap_tuples_scanned,
+ s.param5 AS heap_tuples_written,
+ s.param6 AS heap_blks_total,
+ s.param7 AS heap_blks_scanned,
+ s.param8 AS index_rebuild_count
+ FROM (pg_stat_get_progress_info('REPACK'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
+ LEFT JOIN pg_database d ON ((s.datid = d.oid)));
pg_stat_progress_vacuum| SELECT s.pid,
s.datid,
d.datname,
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index b7115f86104..c976823a3cb 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -76,7 +76,6 @@ INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail');
SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass
ORDER BY 1;
-
SELECT relname, relkind,
EXISTS(SELECT 1 FROM pg_class WHERE oid = c.reltoastrelid) AS hastoast
FROM pg_class c WHERE relname LIKE 'clstr_tst%' ORDER BY relname;
@@ -229,6 +228,24 @@ SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM o
CLUSTER clstrpart;
ALTER TABLE clstrpart SET WITHOUT CLUSTER;
ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+
+-- Check that REPACK sets new relfilenodes: it should process exactly the same
+-- tables as CLUSTER did.
+DROP TABLE old_cluster_info;
+DROP TABLE new_cluster_info;
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+REPACK clstrpart USING INDEX clstrpart_idx;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+
+-- And finally the same for REPACK w/o index.
+DROP TABLE old_cluster_info;
+DROP TABLE new_cluster_info;
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+REPACK clstrpart;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+
DROP TABLE clstrpart;
-- Ownership of partitions is checked
@@ -313,6 +330,57 @@ EXPLAIN (COSTS OFF) SELECT * FROM clstr_expression WHERE -a = -3 ORDER BY -a, b;
SELECT * FROM clstr_expression WHERE -a = -3 ORDER BY -a, b;
COMMIT;
+----------------------------------------------------------------------
+--
+-- REPACK
+--
+----------------------------------------------------------------------
+
+-- REPACK handles individual tables identically to CLUSTER, but it's worth
+-- checking if it handles table hierarchies identically as well.
+REPACK clstr_tst USING INDEX clstr_tst_c;
+
+-- Verify that inheritance link still works
+INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2');
+SELECT a,b,c,substring(d for 30), length(d) from clstr_tst;
+
+-- Verify that foreign key link still works
+INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail');
+
+SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass
+ORDER BY 1;
+
+-- Verify partial analyze works
+REPACK (ANALYZE) clstr_tst (a);
+REPACK (ANALYZE) clstr_tst;
+REPACK (VERBOSE) clstr_tst (a);
+
+-- REPACK w/o argument performs no ordering, so we can only check which tables
+-- have the relfilenode changed.
+RESET SESSION AUTHORIZATION;
+CREATE TEMP TABLE relnodes_old AS
+(SELECT relname, relfilenode
+FROM pg_class
+WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3'));
+
+SET SESSION AUTHORIZATION regress_clstr_user;
+SET client_min_messages = ERROR; -- order of "skipping" warnings may vary
+REPACK;
+RESET client_min_messages;
+
+RESET SESSION AUTHORIZATION;
+CREATE TEMP TABLE relnodes_new AS
+(SELECT relname, relfilenode
+FROM pg_class
+WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3'));
+
+-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been
+-- processed because there is nothing like clustering index here.
+SELECT o.relname FROM relnodes_old o
+JOIN relnodes_new n ON o.relname = n.relname
+WHERE o.relfilenode <> n.relfilenode
+ORDER BY o.relname;
+
-- clean up
DROP TABLE clustertest;
DROP TABLE clstr_1;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9dd65b10254..4f3c7c160a6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2557,6 +2557,8 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepOriginId
+RepackCommand
+RepackStmt
ReparameterizeForeignPathByChild_function
ReplaceVarsFromTargetList_context
ReplaceVarsNoMatchOption
--
2.47.3
[text/x-diff] v28-0002-Refactor-index_concurrently_create_copy-for-use-with.patch (10.2K, ../210036.1765651719@localhost/3-v28-0002-Refactor-index_concurrently_create_copy-for-use-with.patch)
download | inline diff:
From c44fc84b28c599a9c3e484f0b8d5f482305ac5d6 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 2/6] Refactor index_concurrently_create_copy() for use with
REPACK (CONCURRENTLY).
This patch moves the code to index_create_copy() and adds a "concurrently"
parameter so it can be used by REPACK (CONCURRENTLY).
With the CONCURRENTLY option, REPACK cannot simply swap the heap file and
rebuild its indexes. Instead, it needs to build a separate set of indexes
(including system catalog entries) *before* the actual swap, to reduce the
time AccessExclusiveLock needs to be held for.
---
src/backend/catalog/index.c | 54 +++++++++++++++++++++++---------
src/backend/commands/cluster.c | 8 ++---
src/backend/commands/indexcmds.c | 6 ++--
src/backend/nodes/makefuncs.c | 9 +++---
src/include/catalog/index.h | 3 ++
src/include/nodes/makefuncs.h | 4 ++-
6 files changed, 57 insertions(+), 27 deletions(-)
diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index bd77584bc99..60efa77d34f 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -1290,15 +1290,32 @@ index_create(Relation heapRelation,
/*
* index_concurrently_create_copy
*
- * Create concurrently an index based on the definition of the one provided by
- * caller. The index is inserted into catalogs and needs to be built later
- * on. This is called during concurrent reindex processing.
- *
- * "tablespaceOid" is the tablespace to use for this index.
+ * Variant of index_create_copy(), called during concurrent reindex
+ * processing.
*/
Oid
index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
Oid tablespaceOid, const char *newName)
+{
+ return index_create_copy(heapRelation, oldIndexId, tablespaceOid, newName,
+ true);
+}
+
+/*
+ * index_create_copy
+ *
+ * Create an index based on the definition of the one provided by caller. The
+ * index is inserted into catalogs. If 'concurrently' is TRUE, it needs to be
+ * built later on, otherwise it's built immediately.
+ *
+ * "tablespaceOid" is the tablespace to use for this index.
+ *
+ * The actual implementation of index_concurrently_create_copy(), reusable for
+ * other purposes.
+ */
+Oid
+index_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid,
+ const char *newName, bool concurrently)
{
Relation indexRelation;
IndexInfo *oldInfo,
@@ -1317,6 +1334,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
List *indexColNames = NIL;
List *indexExprs = NIL;
List *indexPreds = NIL;
+ int flags = 0;
indexRelation = index_open(oldIndexId, RowExclusiveLock);
@@ -1327,7 +1345,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
* Concurrent build of an index with exclusion constraints is not
* supported.
*/
- if (oldInfo->ii_ExclusionOps != NULL)
+ if (oldInfo->ii_ExclusionOps != NULL && concurrently)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("concurrent index creation for exclusion constraints is not supported")));
@@ -1383,9 +1401,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
}
/*
- * Build the index information for the new index. Note that rebuild of
- * indexes with exclusion constraints is not supported, hence there is no
- * need to fill all the ii_Exclusion* fields.
+ * Build the index information for the new index.
*/
newInfo = makeIndexInfo(oldInfo->ii_NumIndexAttrs,
oldInfo->ii_NumIndexKeyAttrs,
@@ -1394,10 +1410,13 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
indexPreds,
oldInfo->ii_Unique,
oldInfo->ii_NullsNotDistinct,
- false, /* not ready for inserts */
- true,
+ !concurrently, /* isready */
+ concurrently, /* concurrent */
indexRelation->rd_indam->amsummarizing,
- oldInfo->ii_WithoutOverlaps);
+ oldInfo->ii_WithoutOverlaps,
+ oldInfo->ii_ExclusionOps,
+ oldInfo->ii_ExclusionProcs,
+ oldInfo->ii_ExclusionStrats);
/*
* Extract the list of column names and the column numbers for the new
@@ -1435,6 +1454,9 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
stattargets[i].isnull = isnull;
}
+ if (concurrently)
+ flags = INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT;
+
/*
* Now create the new index.
*
@@ -1458,7 +1480,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
indcoloptions->values,
stattargets,
reloptionsDatum,
- INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT,
+ flags,
0,
true, /* allow table to be a system catalog? */
false, /* is_internal? */
@@ -2452,7 +2474,8 @@ BuildIndexInfo(Relation index)
indexStruct->indisready,
false,
index->rd_indam->amsummarizing,
- indexStruct->indisexclusion && indexStruct->indisunique);
+ indexStruct->indisexclusion && indexStruct->indisunique,
+ NULL, NULL, NULL);
/* fill in attribute numbers */
for (i = 0; i < numAtts; i++)
@@ -2512,7 +2535,8 @@ BuildDummyIndexInfo(Relation index)
indexStruct->indisready,
false,
index->rd_indam->amsummarizing,
- indexStruct->indisexclusion && indexStruct->indisunique);
+ indexStruct->indisexclusion && indexStruct->indisunique,
+ NULL, NULL, NULL);
/* fill in attribute numbers */
for (i = 0; i < numAtts; i++)
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 7f772c5c4f8..a2d72ce494d 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -70,8 +70,7 @@ typedef struct
static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap,
Oid indexOid, Oid userid, int options);
-static void rebuild_relation(RepackCommand cmd,
- Relation OldHeap, Relation index, bool verbose);
+static void rebuild_relation(Relation OldHeap, Relation index, bool verbose);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
bool verbose, bool *pSwapToastByContent,
TransactionId *pFreezeXid, MultiXactId *pCutoffMulti);
@@ -415,7 +414,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
TransferPredicateLocksToHeapRelation(OldHeap);
/* rebuild_relation does all the dirty work */
- rebuild_relation(cmd, OldHeap, index, verbose);
+ rebuild_relation(OldHeap, index, verbose);
/* rebuild_relation closes OldHeap, and index if valid */
out:
@@ -629,8 +628,7 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
* On exit, they are closed, but locks on them are not released.
*/
static void
-rebuild_relation(RepackCommand cmd,
- Relation OldHeap, Relation index, bool verbose)
+rebuild_relation(Relation OldHeap, Relation index, bool verbose)
{
Oid tableOid = RelationGetRelid(OldHeap);
Oid accessMethod = OldHeap->rd_rel->relam;
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index d9cccb6ac18..d8d8f72a875 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -242,7 +242,8 @@ CheckIndexCompatible(Oid oldId,
*/
indexInfo = makeIndexInfo(numberOfAttributes, numberOfAttributes,
accessMethodId, NIL, NIL, false, false,
- false, false, amsummarizing, isWithoutOverlaps);
+ false, false, amsummarizing, isWithoutOverlaps,
+ NULL, NULL, NULL);
typeIds = palloc_array(Oid, numberOfAttributes);
collationIds = palloc_array(Oid, numberOfAttributes);
opclassIds = palloc_array(Oid, numberOfAttributes);
@@ -927,7 +928,8 @@ DefineIndex(Oid tableId,
!concurrent,
concurrent,
amissummarizing,
- stmt->iswithoutoverlaps);
+ stmt->iswithoutoverlaps,
+ NULL, NULL, NULL);
typeIds = palloc_array(Oid, numberOfAttributes);
collationIds = palloc_array(Oid, numberOfAttributes);
diff --git a/src/backend/nodes/makefuncs.c b/src/backend/nodes/makefuncs.c
index e2d9e9be41a..c5d5a37f514 100644
--- a/src/backend/nodes/makefuncs.c
+++ b/src/backend/nodes/makefuncs.c
@@ -834,7 +834,8 @@ IndexInfo *
makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
List *predicates, bool unique, bool nulls_not_distinct,
bool isready, bool concurrent, bool summarizing,
- bool withoutoverlaps)
+ bool withoutoverlaps, Oid *exclusion_ops, Oid *exclusion_procs,
+ uint16 *exclusion_strats)
{
IndexInfo *n = makeNode(IndexInfo);
@@ -863,9 +864,9 @@ makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
n->ii_PredicateState = NULL;
/* exclusion constraints */
- n->ii_ExclusionOps = NULL;
- n->ii_ExclusionProcs = NULL;
- n->ii_ExclusionStrats = NULL;
+ n->ii_ExclusionOps = exclusion_ops;
+ n->ii_ExclusionProcs = exclusion_procs;
+ n->ii_ExclusionStrats = exclusion_strats;
/* speculative inserts */
n->ii_UniqueOps = NULL;
diff --git a/src/include/catalog/index.h b/src/include/catalog/index.h
index dda95e54903..4bf909078d8 100644
--- a/src/include/catalog/index.h
+++ b/src/include/catalog/index.h
@@ -99,6 +99,9 @@ extern Oid index_concurrently_create_copy(Relation heapRelation,
Oid oldIndexId,
Oid tablespaceOid,
const char *newName);
+extern Oid index_create_copy(Relation heapRelation, Oid oldIndexId,
+ Oid tablespaceOid, const char *newName,
+ bool concurrently);
extern void index_concurrently_build(Oid heapRelationId,
Oid indexRelationId);
diff --git a/src/include/nodes/makefuncs.h b/src/include/nodes/makefuncs.h
index 5473ce9a288..9ff7159ff0c 100644
--- a/src/include/nodes/makefuncs.h
+++ b/src/include/nodes/makefuncs.h
@@ -99,7 +99,9 @@ extern IndexInfo *makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid,
List *expressions, List *predicates,
bool unique, bool nulls_not_distinct,
bool isready, bool concurrent,
- bool summarizing, bool withoutoverlaps);
+ bool summarizing, bool withoutoverlaps,
+ Oid *exclusion_ops, Oid *exclusion_procs,
+ uint16 *exclusion_strats);
extern Node *makeStringConst(char *str, int location);
extern DefElem *makeDefElem(char *name, Node *arg, int location);
--
2.47.3
[text/x-diff] v28-0003-Move-conversion-of-a-historic-to-MVCC-snapshot-to-a-.patch (5.5K, ../210036.1765651719@localhost/4-v28-0003-Move-conversion-of-a-historic-to-MVCC-snapshot-to-a-.patch)
download | inline diff:
From 34a13e3fabc89d2952393f37d2b1388e96c9c7c2 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 3/6] Move conversion of a "historic" to MVCC snapshot to a
separate function.
The conversion is now handled by SnapBuildMVCCFromHistoric(). REPACK
CONCURRENTLY will also need it.
---
src/backend/replication/logical/snapbuild.c | 57 +++++++++++++++++----
src/backend/utils/time/snapmgr.c | 3 +-
src/include/replication/snapbuild.h | 1 +
src/include/utils/snapmgr.h | 1 +
4 files changed, 50 insertions(+), 12 deletions(-)
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index d6ab1e017eb..a3730804428 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -440,10 +440,7 @@ Snapshot
SnapBuildInitialSnapshot(SnapBuild *builder)
{
Snapshot snap;
- TransactionId xid;
TransactionId safeXid;
- TransactionId *newxip;
- int newxcnt = 0;
Assert(XactIsoLevel == XACT_REPEATABLE_READ);
Assert(builder->building_full_snapshot);
@@ -485,7 +482,33 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
MyProc->xmin = snap->xmin;
- /* allocate in transaction context */
+ /* Convert the historic snapshot to MVCC snapshot. */
+ return SnapBuildMVCCFromHistoric(snap, true);
+}
+
+/*
+ * Turn a historic MVCC snapshot into an ordinary MVCC snapshot.
+ *
+ * Unlike a regular (non-historic) MVCC snapshot, the 'xip' array of this
+ * snapshot contains not only running main transactions, but also their
+ * subtransactions. On the other hand, 'subxip' will usually be empty. This
+ * difference does not affect the result of XidInMVCCSnapshot() because it
+ * searches both in 'xip' and 'subxip'.
+ *
+ * Pass true for 'in_place' if you don't care about modifying the source
+ * snapshot. If you need a new instance, and one that was allocated as a
+ * single chunk of memory, pass false.
+ */
+Snapshot
+SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place)
+{
+ TransactionId xid;
+ TransactionId *oldxip = snapshot->xip;
+ uint32 oldxcnt = snapshot->xcnt;
+ TransactionId *newxip;
+ int newxcnt = 0;
+ Snapshot result;
+
newxip = palloc_array(TransactionId, GetMaxSnapshotXidCount());
/*
@@ -494,7 +517,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
* classical snapshot by marking all non-committed transactions as
* in-progress. This can be expensive.
*/
- for (xid = snap->xmin; NormalTransactionIdPrecedes(xid, snap->xmax);)
+ for (xid = snapshot->xmin; NormalTransactionIdPrecedes(xid, snapshot->xmax);)
{
void *test;
@@ -502,7 +525,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
* Check whether transaction committed using the decoding snapshot
* meaning of ->xip.
*/
- test = bsearch(&xid, snap->xip, snap->xcnt,
+ test = bsearch(&xid, snapshot->xip, snapshot->xcnt,
sizeof(TransactionId), xidComparator);
if (test == NULL)
@@ -519,11 +542,25 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
}
/* adjust remaining snapshot fields as needed */
- snap->snapshot_type = SNAPSHOT_MVCC;
- snap->xcnt = newxcnt;
- snap->xip = newxip;
+ snapshot->xcnt = newxcnt;
+ snapshot->xip = newxip;
+
+ if (in_place)
+ result = snapshot;
+ else
+ {
+ result = CopySnapshot(snapshot);
+
+ /* Restore the original values so the source is intact. */
+ snapshot->xip = oldxip;
+ snapshot->xcnt = oldxcnt;
+
+ /* newxip has been copied */
+ pfree(newxip);
+ }
+ result->snapshot_type = SNAPSHOT_MVCC;
- return snap;
+ return result;
}
/*
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index 40a2e90e071..4cf32ffe833 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -213,7 +213,6 @@ typedef struct ExportedSnapshot
static List *exportedSnapshots = NIL;
/* Prototypes for local functions */
-static Snapshot CopySnapshot(Snapshot snapshot);
static void UnregisterSnapshotNoOwner(Snapshot snapshot);
static void FreeSnapshot(Snapshot snapshot);
static void SnapshotResetXmin(void);
@@ -604,7 +603,7 @@ SetTransactionSnapshot(Snapshot sourcesnap, VirtualTransactionId *sourcevxid,
* The copy is palloc'd in TopTransactionContext and has initial refcounts set
* to 0. The returned snapshot has the copied flag set.
*/
-static Snapshot
+Snapshot
CopySnapshot(Snapshot snapshot)
{
Snapshot newsnap;
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 44031dcf6e3..6d4d2d1814c 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,6 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
extern void SnapBuildSnapDecRefcount(Snapshot snap);
extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
+extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
extern void SnapBuildClearExportedSnapshot(void);
extern void SnapBuildResetExportedSnapshotState(void);
diff --git a/src/include/utils/snapmgr.h b/src/include/utils/snapmgr.h
index 604c1f90216..f65f83c85cd 100644
--- a/src/include/utils/snapmgr.h
+++ b/src/include/utils/snapmgr.h
@@ -63,6 +63,7 @@ extern Snapshot GetTransactionSnapshot(void);
extern Snapshot GetLatestSnapshot(void);
extern void SnapshotSetCommandId(CommandId curcid);
+extern Snapshot CopySnapshot(Snapshot snapshot);
extern Snapshot GetCatalogSnapshot(Oid relid);
extern Snapshot GetNonHistoricCatalogSnapshot(Oid relid);
extern void InvalidateCatalogSnapshot(void);
--
2.47.3
[text/plain] v28-0004-Add-CONCURRENTLY-option-to-REPACK-command.patch (145.3K, ../210036.1765651719@localhost/5-v28-0004-Add-CONCURRENTLY-option-to-REPACK-command.patch)
download | inline diff:
From 6279394135f2b693b6fffd174822509e0a067cbf Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 4/6] Add CONCURRENTLY option to REPACK command.
The REPACK command copies the relation data into a new file, creates new
indexes and eventually swaps the files. To make sure that the old file does
not change during the copying, the relation is locked in an exclusive mode,
which prevents applications from both reading and writing. (To keep the data
consistent, we'd only need to prevent the applications from writing, but even
reading needs to be blocked before we can swap the files - otherwise some
applications could continue using the old file. Since we should not request a
stronger lock without releasing the weaker one first, we acquire the exclusive
lock in the beginning and keep it till the end of the processing.)
This patch introduces an alternative workflow, which only requires the
exclusive lock when the relation (and index) files are being swapped.
(Supposedly, the swapping should be pretty fast.) On the other hand, when we
copy the data to the new file, we allow applications to read from the relation
and even to write to it.
First, we scan the relation using a "historic snapshot", and insert all the
tuples satisfying this snapshot into the new file.
Second, logical decoding is used to capture the data changes done by
applications during the copying (i.e. changes that do not satisfy the historic
snapshot mentioned above), and those are applied to the new file before we
acquire the exclusive lock that we need to swap the files. (Of course, more
data changes can take place while we are waiting for the lock - these will be
applied to the new file after we have acquired the lock, before we swap the
files.)
Since the logical decoding system, during its startup, waits until all the
transactions which already have XID assigned have finished, there is a risk of
deadlock if a transaction that already changed anything in the database tries
to acquire a conflicting lock on the table REPACK CONCURRENTLY is working
on. As an example, consider transaction running CREATE INDEX command on the
table that is being REPACKed CONCURRENTLY. On the other hand, DML commands
(INSERT, UPDATE, DELETE) are not a problem as their lock does not conflict
with REPACK CONCURRENTLY.
The current approach is that we accept the risk. If we tried to avoid it, it'd
be necessary to unlock the table before the logical decoding is setup and lock
it again afterwards. Such temporary unlocking would imply re-checking if the
table still meets all the requirements for REPACK CONCURRENTLY.
Like the existing implementation of REPACK, the variant with the CONCURRENTLY
option also requires an extra space for the new relation and index files
(which coexist with the old files for some time). In addition, the
CONCURRENTLY option might introduce a lag in releasing WAL segments for
archiving / recycling. This is due to the decoding of the data changes done by
applications concurrently. When copying the table contents into the new file,
we check the lag periodically. If it exceeds the size of a WAL segment, we
decode all the available WAL before resuming the copying. (Of course, the
changes are not applied until the whole table contents is copied.) A
background worker might be a better approach for the decoding - let's consider
implementing it in the future.
The WAL records produced by running DML commands on the new relation do not
contain enough information to be processed by the logical decoding system. All
we need from the new relation is the file (relfilenode), while the actual
relation is eventually dropped. Thus there is no point in replaying the DMLs
anywhere.
---
doc/src/sgml/monitoring.sgml | 37 +-
doc/src/sgml/mvcc.sgml | 12 +-
doc/src/sgml/ref/repack.sgml | 129 +-
src/Makefile | 1 +
src/backend/access/heap/heapam.c | 34 +-
src/backend/access/heap/heapam_handler.c | 227 ++-
src/backend/access/heap/rewriteheap.c | 6 +-
src/backend/catalog/system_views.sql | 19 +-
src/backend/commands/cluster.c | 1599 +++++++++++++++--
src/backend/commands/matview.c | 2 +-
src/backend/commands/tablecmds.c | 1 +
src/backend/commands/vacuum.c | 12 +-
src/backend/meson.build | 1 +
src/backend/replication/logical/decode.c | 94 +
src/backend/replication/logical/snapbuild.c | 21 +
.../replication/pgoutput_repack/Makefile | 32 +
.../replication/pgoutput_repack/meson.build | 18 +
.../pgoutput_repack/pgoutput_repack.c | 240 +++
.../storage/lmgr/generate-lwlocknames.pl | 2 +-
src/backend/utils/time/snapmgr.c | 3 +-
src/bin/psql/tab-complete.in.c | 4 +-
src/include/access/heapam.h | 5 +-
src/include/access/heapam_xlog.h | 2 +
src/include/access/tableam.h | 10 +
src/include/commands/cluster.h | 90 +-
src/include/commands/progress.h | 17 +-
src/include/replication/snapbuild.h | 1 +
src/include/storage/lockdefs.h | 4 +-
src/include/utils/snapmgr.h | 2 +
src/test/modules/injection_points/Makefile | 3 +
.../injection_points/expected/repack.out | 113 ++
.../expected/repack_toast.out | 64 +
.../modules/injection_points/logical.conf | 1 +
src/test/modules/injection_points/meson.build | 4 +
.../injection_points/specs/repack.spec | 142 ++
.../injection_points/specs/repack_toast.spec | 105 ++
src/test/regress/expected/rules.out | 19 +-
src/tools/pgindent/typedefs.list | 5 +
38 files changed, 2845 insertions(+), 236 deletions(-)
create mode 100644 src/backend/replication/pgoutput_repack/Makefile
create mode 100644 src/backend/replication/pgoutput_repack/meson.build
create mode 100644 src/backend/replication/pgoutput_repack/pgoutput_repack.c
create mode 100644 src/test/modules/injection_points/expected/repack.out
create mode 100644 src/test/modules/injection_points/expected/repack_toast.out
create mode 100644 src/test/modules/injection_points/logical.conf
create mode 100644 src/test/modules/injection_points/specs/repack.spec
create mode 100644 src/test/modules/injection_points/specs/repack_toast.spec
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index b07fe3294cd..ae56b09aeba 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -6202,14 +6202,35 @@ FROM pg_stat_get_backend_idset() AS backendid;
<row>
<entry role="catalog_table_entry"><para role="column_definition">
- <structfield>heap_tuples_written</structfield> <type>bigint</type>
+ <structfield>heap_tuples_inserted</structfield> <type>bigint</type>
</para>
<para>
- Number of heap tuples written.
+ Number of heap tuples inserted.
This counter only advances when the phase is
<literal>seq scanning heap</literal>,
- <literal>index scanning heap</literal>
- or <literal>writing new heap</literal>.
+ <literal>index scanning heap</literal>,
+ <literal>writing new heap</literal>
+ or <literal>catch-up</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_updated</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples updated.
+ This counter only advances when the phase is <literal>catch-up</literal>.
+ </para></entry>
+ </row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>heap_tuples_deleted</structfield> <type>bigint</type>
+ </para>
+ <para>
+ Number of heap tuples deleted.
+ This counter only advances when the phase is <literal>catch-up</literal>.
</para></entry>
</row>
@@ -6290,6 +6311,14 @@ FROM pg_stat_get_backend_idset() AS backendid;
<command>REPACK</command> is currently writing the new heap.
</entry>
</row>
+ <row>
+ <entry><literal>catch-up</literal></entry>
+ <entry>
+ <command>REPACK CONCURRENTLY</command> is currently processing the DML
+ commands that other transactions executed during any of the preceding
+ phases.
+ </entry>
+ </row>
<row>
<entry><literal>swapping relation files</literal></entry>
<entry>
diff --git a/doc/src/sgml/mvcc.sgml b/doc/src/sgml/mvcc.sgml
index 049ee75a4ba..0f5c34af542 100644
--- a/doc/src/sgml/mvcc.sgml
+++ b/doc/src/sgml/mvcc.sgml
@@ -1833,15 +1833,17 @@ SELECT pg_advisory_lock(q.id) FROM
<title>Caveats</title>
<para>
- Some DDL commands, currently only <link linkend="sql-truncate"><command>TRUNCATE</command></link> and the
- table-rewriting forms of <link linkend="sql-altertable"><command>ALTER TABLE</command></link>, are not
+ Some commands, currently only <link linkend="sql-truncate"><command>TRUNCATE</command></link>, the
+ table-rewriting forms of <link linkend="sql-altertable"><command>ALTER
+ TABLE</command></link> and <command>REPACK</command> with
+ the <literal>CONCURRENTLY</literal> option, are not
MVCC-safe. This means that after the truncation or rewrite commits, the
table will appear empty to concurrent transactions, if they are using a
- snapshot taken before the DDL command committed. This will only be an
+ snapshot taken before the command committed. This will only be an
issue for a transaction that did not access the table in question
- before the DDL command started — any transaction that has done so
+ before the command started — any transaction that has done so
would hold at least an <literal>ACCESS SHARE</literal> table lock,
- which would block the DDL command until that transaction completes.
+ which would block the truncating or rewriting command until that transaction completes.
So these commands will not cause any apparent inconsistency in the
table contents for successive queries on the target table, but they
could cause visible inconsistency between the contents of the target
diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml
index 61d5c2cdef1..30c43c49069 100644
--- a/doc/src/sgml/ref/repack.sgml
+++ b/doc/src/sgml/ref/repack.sgml
@@ -28,6 +28,7 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
VERBOSE [ <replaceable class="parameter">boolean</replaceable> ]
ANALYZE [ <replaceable class="parameter">boolean</replaceable> ]
+ CONCURRENTLY [ <replaceable class="parameter">boolean</replaceable> ]
<phrase>and <replaceable class="parameter">table_and_columns</replaceable> is:</phrase>
@@ -54,7 +55,8 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
processes every table and materialized view in the current database that
the current user has the <literal>MAINTAIN</literal> privilege on. This
form of <command>REPACK</command> cannot be executed inside a transaction
- block.
+ block. Also, this form is not allowed if
+ the <literal>CONCURRENTLY</literal> option is used.
</para>
<para>
@@ -67,7 +69,8 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
When a table is being repacked, an <literal>ACCESS EXCLUSIVE</literal> lock
is acquired on it. This prevents any other database operations (both reads
and writes) from operating on the table until the <command>REPACK</command>
- is finished.
+ is finished. If you want to keep the table accessible during the repacking,
+ consider using the <literal>CONCURRENTLY</literal> option.
</para>
<refsect2 id="sql-repack-notes-on-clustering" xreflabel="Notes on Clustering">
@@ -195,6 +198,128 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
</listitem>
</varlistentry>
+ <varlistentry>
+ <term><literal>CONCURRENTLY</literal></term>
+ <listitem>
+ <para>
+ Allow other transactions to use the table while it is being repacked.
+ </para>
+
+ <para>
+ Internally, <command>REPACK</command> copies the contents of the table
+ (ignoring dead tuples) into a new file, sorted by the specified index,
+ and also creates a new file for each index. Then it swaps the old and
+ new files for the table and all the indexes, and deletes the old
+ files. The <literal>ACCESS EXCLUSIVE</literal> lock is needed to make
+ sure that the old files do not change during the processing because the
+ changes would get lost due to the swap.
+ </para>
+
+ <para>
+ With the <literal>CONCURRENTLY</literal> option, the <literal>ACCESS
+ EXCLUSIVE</literal> lock is only acquired to swap the table and index
+ files. The data changes that took place during the creation of the new
+ table and index files are captured using logical decoding
+ (<xref linkend="logicaldecoding"/>) and applied before
+ the <literal>ACCESS EXCLUSIVE</literal> lock is requested. Thus the lock
+ is typically held only for the time needed to swap the files, which
+ should be pretty short. However, the time might still be noticeable if
+ too many data changes have been done to the table while
+ <command>REPACK</command> was waiting for the lock: those changes must
+ be processed just before the files are swapped, while the
+ <literal>ACCESS EXCLUSIVE</literal> lock is being held.
+ </para>
+
+ <para>
+ Note that <command>REPACK</command> with the
+ <literal>CONCURRENTLY</literal> option does not try to order the rows
+ inserted into the table after the repacking started. Also
+ note <command>REPACK</command> might fail to complete due to DDL
+ commands executed on the table by other transactions during the
+ repacking.
+ </para>
+
+ <note>
+ <para>
+ In addition to the temporary space requirements explained in
+ <xref linkend="sql-repack-notes-on-resources"/>,
+ the <literal>CONCURRENTLY</literal> option can add to the usage of
+ temporary space a bit more. The reason is that other transactions can
+ perform DML operations which cannot be applied to the new file until
+ <command>REPACK</command> has copied all the tuples from the old
+ file. Thus the tuples inserted into the old file during the copying are
+ also stored separately in a temporary file, so they can eventually be
+ applied to the new file.
+ </para>
+
+ <para>
+ Furthermore, the data changes performed during the copying are
+ extracted from <link linkend="wal">write-ahead log</link> (WAL), and
+ this extraction (decoding) only takes place when certain amount of WAL
+ has been written. Therefore, WAL removal can be delayed by this
+ threshold. Currently the threshold is equal to the value of
+ the <link linkend="guc-wal-segment-size"><varname>wal_segment_size</varname></link>
+ configuration parameter.
+ </para>
+ </note>
+
+ <para>
+ The <literal>CONCURRENTLY</literal> option cannot be used in the
+ following cases:
+
+ <itemizedlist>
+ <listitem>
+ <para>
+ The table is <literal>UNLOGGED</literal>.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The table is partitioned.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The table is a system catalog or a <acronym>TOAST</acronym> table.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ <command>REPACK</command> is executed inside a transaction block.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The <link linkend="guc-wal-level"><varname>wal_level</varname></link>
+ configuration parameter is less than <literal>logical</literal>.
+ </para>
+ </listitem>
+
+ <listitem>
+ <para>
+ The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link>
+ configuration parameter does not allow for creation of an additional
+ replication slot.
+ </para>
+ </listitem>
+ </itemizedlist>
+ </para>
+
+ <warning>
+ <para>
+ <command>REPACK</command> with the <literal>CONCURRENTLY</literal>
+ option is not MVCC-safe, see <xref linkend="mvcc-caveats"/> for
+ details.
+ </para>
+ </warning>
+
+ </listitem>
+ </varlistentry>
+
<varlistentry>
<term><literal>VERBOSE</literal></term>
<listitem>
diff --git a/src/Makefile b/src/Makefile
index 2f31a2f20a7..b18c9a14ffa 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -23,6 +23,7 @@ SUBDIRS = \
interfaces \
backend/replication/libpqwalreceiver \
backend/replication/pgoutput \
+ backend/replication/pgoutput_repack \
fe_utils \
bin \
pl \
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 225f9829f22..aa2b4ca3f0a 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -60,7 +60,8 @@ static HeapTuple heap_prepare_insert(Relation relation, HeapTuple tup,
static XLogRecPtr log_heap_update(Relation reln, Buffer oldbuf,
Buffer newbuf, HeapTuple oldtup,
HeapTuple newtup, HeapTuple old_key_tuple,
- bool all_visible_cleared, bool new_all_visible_cleared);
+ bool all_visible_cleared, bool new_all_visible_cleared,
+ bool walLogical);
#ifdef USE_ASSERT_CHECKING
static void check_lock_if_inplace_updateable_rel(Relation relation,
const ItemPointerData *otid,
@@ -2803,7 +2804,7 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask)
TM_Result
heap_delete(Relation relation, const ItemPointerData *tid,
CommandId cid, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart)
+ TM_FailureData *tmfd, bool changingPart, bool walLogical)
{
TM_Result result;
TransactionId xid = GetCurrentTransactionId();
@@ -3050,7 +3051,8 @@ l1:
* Compute replica identity tuple before entering the critical section so
* we don't PANIC upon a memory allocation failure.
*/
- old_key_tuple = ExtractReplicaIdentity(relation, &tp, true, &old_key_copied);
+ old_key_tuple = walLogical ?
+ ExtractReplicaIdentity(relation, &tp, true, &old_key_copied) : NULL;
/*
* If this is the first possibly-multixact-able operation in the current
@@ -3140,6 +3142,15 @@ l1:
xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
}
+ /*
+ * Unlike UPDATE, DELETE is decoded even if there is no old key, so it
+ * does not help to clear both XLH_DELETE_CONTAINS_OLD_TUPLE and
+ * XLH_DELETE_CONTAINS_OLD_KEY. Thus we need an extra flag. TODO
+ * Consider not decoding tuples w/o the old tuple/key instead.
+ */
+ if (!walLogical)
+ xlrec.flags |= XLH_DELETE_NO_LOGICAL;
+
XLogBeginInsert();
XLogRegisterData(&xlrec, SizeOfHeapDelete);
@@ -3232,7 +3243,8 @@ simple_heap_delete(Relation relation, const ItemPointerData *tid)
result = heap_delete(relation, tid,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
- &tmfd, false /* changingPart */ );
+ &tmfd, false, /* changingPart */
+ true /* walLogical */ );
switch (result)
{
case TM_SelfModified:
@@ -3273,7 +3285,7 @@ TM_Result
heap_update(Relation relation, const ItemPointerData *otid, HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
TM_FailureData *tmfd, LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes)
+ TU_UpdateIndexes *update_indexes, bool walLogical)
{
TM_Result result;
TransactionId xid = GetCurrentTransactionId();
@@ -4166,7 +4178,8 @@ l2:
newbuf, &oldtup, heaptup,
old_key_tuple,
all_visible_cleared,
- all_visible_cleared_new);
+ all_visible_cleared_new,
+ walLogical);
if (newbuf != buffer)
{
PageSetLSN(BufferGetPage(newbuf), recptr);
@@ -4524,7 +4537,8 @@ simple_heap_update(Relation relation, const ItemPointerData *otid, HeapTuple tup
result = heap_update(relation, otid, tup,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
- &tmfd, &lockmode, update_indexes);
+ &tmfd, &lockmode, update_indexes,
+ true /* walLogical */ );
switch (result)
{
case TM_SelfModified:
@@ -8864,7 +8878,8 @@ static XLogRecPtr
log_heap_update(Relation reln, Buffer oldbuf,
Buffer newbuf, HeapTuple oldtup, HeapTuple newtup,
HeapTuple old_key_tuple,
- bool all_visible_cleared, bool new_all_visible_cleared)
+ bool all_visible_cleared, bool new_all_visible_cleared,
+ bool walLogical)
{
xl_heap_update xlrec;
xl_heap_header xlhdr;
@@ -8875,7 +8890,8 @@ log_heap_update(Relation reln, Buffer oldbuf,
suffixlen = 0;
XLogRecPtr recptr;
Page page = BufferGetPage(newbuf);
- bool need_tuple_data = RelationIsLogicallyLogged(reln);
+ bool need_tuple_data = RelationIsLogicallyLogged(reln) &&
+ walLogical;
bool init;
int bufflags;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index b3a19003cdd..6063e037edb 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -33,6 +33,7 @@
#include "catalog/index.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
+#include "commands/cluster.h"
#include "commands/progress.h"
#include "executor/executor.h"
#include "miscadmin.h"
@@ -309,7 +310,8 @@ heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid,
* the storage itself is cleaning the dead tuples by itself, it is the
* time to call the index tuple deletion also.
*/
- return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart);
+ return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart,
+ true);
}
@@ -328,7 +330,7 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot,
tuple->t_tableOid = slot->tts_tableOid;
result = heap_update(relation, otid, tuple, cid, crosscheck, wait,
- tmfd, lockmode, update_indexes);
+ tmfd, lockmode, update_indexes, true);
ItemPointerCopy(&tuple->t_self, &slot->tts_tid);
/*
@@ -685,13 +687,15 @@ static void
heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
Relation OldIndex, bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
double *tups_recently_dead)
{
- RewriteState rwstate;
+ RewriteState rwstate = NULL;
IndexScanDesc indexScan;
TableScanDesc tableScan;
HeapScanDesc heapScan;
@@ -705,6 +709,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
bool *isnull;
BufferHeapTupleTableSlot *hslot;
BlockNumber prev_cblock = InvalidBlockNumber;
+ bool concurrent = snapshot != NULL;
+ XLogRecPtr end_of_wal_prev = GetFlushRecPtr(NULL);
/* Remember if it's a system catalog */
is_system_catalog = IsSystemRelation(OldHeap);
@@ -720,9 +726,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
values = palloc_array(Datum, natts);
isnull = palloc_array(bool, natts);
- /* Initialize the rewrite operation */
- rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff,
- *multi_cutoff);
+ /*
+ * Initialize the rewrite operation.
+ */
+ if (!concurrent)
+ rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
+ *xid_cutoff, *multi_cutoff);
/* Set up sorting if wanted */
@@ -737,6 +746,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* Prepare to scan the OldHeap. To ensure we see recently-dead tuples
* that still need to be copied, we scan with SnapshotAny and use
* HeapTupleSatisfiesVacuum for the visibility test.
+ *
+ * In the CONCURRENTLY case, we do regular MVCC visibility tests, using
+ * the snapshot passed by the caller.
*/
if (OldIndex != NULL && !use_sort)
{
@@ -753,7 +765,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
tableScan = NULL;
heapScan = NULL;
- indexScan = index_beginscan(OldHeap, OldIndex, SnapshotAny, NULL, 0, 0);
+ indexScan = index_beginscan(OldHeap, OldIndex,
+ snapshot ? snapshot : SnapshotAny,
+ NULL, 0, 0);
index_rescan(indexScan, NULL, 0, NULL, 0);
}
else
@@ -762,7 +776,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP);
- tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL);
+ tableScan = table_beginscan(OldHeap,
+ snapshot ? snapshot : SnapshotAny,
+ 0, (ScanKey) NULL);
heapScan = (HeapScanDesc) tableScan;
indexScan = NULL;
@@ -837,70 +853,77 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
tuple = ExecFetchSlotHeapTuple(slot, false, NULL);
buf = hslot->buffer;
- LockBuffer(buf, BUFFER_LOCK_SHARE);
-
- switch (HeapTupleSatisfiesVacuum(tuple, OldestXmin, buf))
+ /*
+ * Regarding CONCURRENTLY, see the comments on MVCC snapshot above.
+ */
+ if (!concurrent)
{
- case HEAPTUPLE_DEAD:
- /* Definitely dead */
- isdead = true;
- break;
- case HEAPTUPLE_RECENTLY_DEAD:
- *tups_recently_dead += 1;
- /* fall through */
- case HEAPTUPLE_LIVE:
- /* Live or recently dead, must copy it */
- isdead = false;
- break;
- case HEAPTUPLE_INSERT_IN_PROGRESS:
+ LockBuffer(buf, BUFFER_LOCK_SHARE);
- /*
- * Since we hold exclusive lock on the relation, normally the
- * only way to see this is if it was inserted earlier in our
- * own transaction. However, it can happen in system
- * catalogs, since we tend to release write lock before commit
- * there. Give a warning if neither case applies; but in any
- * case we had better copy it.
- */
- if (!is_system_catalog &&
- !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple->t_data)))
- elog(WARNING, "concurrent insert in progress within table \"%s\"",
- RelationGetRelationName(OldHeap));
- /* treat as live */
- isdead = false;
- break;
- case HEAPTUPLE_DELETE_IN_PROGRESS:
+ switch (HeapTupleSatisfiesVacuum(tuple, OldestXmin, buf))
+ {
+ case HEAPTUPLE_DEAD:
+ /* Definitely dead */
+ isdead = true;
+ break;
+ case HEAPTUPLE_RECENTLY_DEAD:
+ *tups_recently_dead += 1;
+ /* fall through */
+ case HEAPTUPLE_LIVE:
+ /* Live or recently dead, must copy it */
+ isdead = false;
+ break;
+ case HEAPTUPLE_INSERT_IN_PROGRESS:
- /*
- * Similar situation to INSERT_IN_PROGRESS case.
- */
- if (!is_system_catalog &&
- !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tuple->t_data)))
- elog(WARNING, "concurrent delete in progress within table \"%s\"",
- RelationGetRelationName(OldHeap));
- /* treat as recently dead */
- *tups_recently_dead += 1;
- isdead = false;
- break;
- default:
- elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
- isdead = false; /* keep compiler quiet */
- break;
- }
+ /*
+ * As long as we hold exclusive lock on the relation,
+ * normally the only way to see this is if it was inserted
+ * earlier in our own transaction. However, it can happen
+ * in system catalogs, since we tend to release write lock
+ * before commit there. Give a warning if neither case
+ * applies; but in any case we had better copy it.
+ */
+ if (!is_system_catalog &&
+ !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple->t_data)))
+ elog(WARNING, "concurrent insert in progress within table \"%s\"",
+ RelationGetRelationName(OldHeap));
+ /* treat as live */
+ isdead = false;
+ break;
+ case HEAPTUPLE_DELETE_IN_PROGRESS:
+
+ /*
+ * Similar situation to INSERT_IN_PROGRESS case.
+ */
+ if (!is_system_catalog &&
+ !TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetUpdateXid(tuple->t_data)))
+ elog(WARNING, "concurrent delete in progress within table \"%s\"",
+ RelationGetRelationName(OldHeap));
+ /* treat as recently dead */
+ *tups_recently_dead += 1;
+ isdead = false;
+ break;
+ default:
+ elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
+ isdead = false; /* keep compiler quiet */
+ break;
+ }
- LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+ LockBuffer(buf, BUFFER_LOCK_UNLOCK);
- if (isdead)
- {
- *tups_vacuumed += 1;
- /* heap rewrite module still needs to see it... */
- if (rewrite_heap_dead_tuple(rwstate, tuple))
+ if (isdead)
{
- /* A previous recently-dead tuple is now known dead */
*tups_vacuumed += 1;
- *tups_recently_dead -= 1;
+ /* heap rewrite module still needs to see it... */
+ if (rewrite_heap_dead_tuple(rwstate, tuple))
+ {
+ /* A previous recently-dead tuple is now known dead */
+ *tups_vacuumed += 1;
+ *tups_recently_dead -= 1;
+ }
+
+ continue;
}
- continue;
}
*num_tuples += 1;
@@ -919,7 +942,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
{
const int ct_index[] = {
PROGRESS_REPACK_HEAP_TUPLES_SCANNED,
- PROGRESS_REPACK_HEAP_TUPLES_WRITTEN
+ PROGRESS_REPACK_HEAP_TUPLES_INSERTED
};
int64 ct_val[2];
@@ -934,6 +957,31 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
ct_val[1] = *num_tuples;
pgstat_progress_update_multi_param(2, ct_index, ct_val);
}
+
+ /*
+ * Process the WAL produced by the load, as well as by other
+ * transactions, so that the replication slot can advance and WAL does
+ * not pile up. Use wal_segment_size as a threshold so that we do not
+ * introduce the decoding overhead too often.
+ *
+ * Of course, we must not apply the changes until the initial load has
+ * completed.
+ *
+ * Note that our insertions into the new table should not be decoded
+ * as we (intentionally) do not write the logical decoding specific
+ * information to WAL.
+ */
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ end_of_wal = GetFlushRecPtr(NULL);
+ if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
+ {
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+ end_of_wal_prev = end_of_wal;
+ }
+ }
}
if (indexScan != NULL)
@@ -977,15 +1025,32 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
values, isnull,
rwstate);
/* Report n_tuples */
- pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_WRITTEN,
+ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
n_tuples);
+
+ /*
+ * Try to keep the amount of not-yet-decoded WAL small, like
+ * above.
+ */
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ end_of_wal = GetFlushRecPtr(NULL);
+ if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
+ {
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+ end_of_wal_prev = end_of_wal;
+ }
+ }
}
tuplesort_end(tuplesort);
}
/* Write out any remaining tuples, and fsync if needed */
- end_heap_rewrite(rwstate);
+ if (rwstate)
+ end_heap_rewrite(rwstate);
/* Clean up */
pfree(values);
@@ -2376,6 +2441,10 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
* SET WITHOUT OIDS.
*
* So, we must reconstruct the tuple from component Datums.
+ *
+ * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
+ * case we still need to deform/form the tuple. TODO Shouldn't we rename the
+ * function, as might not do any rewrite?
*/
static void
reform_and_rewrite_tuple(HeapTuple tuple,
@@ -2398,8 +2467,28 @@ reform_and_rewrite_tuple(HeapTuple tuple,
copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
- /* The heap rewrite module does the rest */
- rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+ if (rwstate)
+ /* The heap rewrite module does the rest */
+ rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+ else
+ {
+ /*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * The following is like simple_heap_insert() except that we pass the
+ * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
+ * the relation files, it drops this relation, so no logical
+ * replication subscription should need the data.
+ */
+ heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
+ HEAP_INSERT_NO_LOGICAL, NULL);
+ }
heap_freetuple(copiedTuple);
}
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index 7ce3c5e2685..ef428486030 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -617,9 +617,9 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
int options = HEAP_INSERT_SKIP_FSM;
/*
- * While rewriting the heap for VACUUM FULL / CLUSTER, make sure data
- * for the TOAST table are not logically decoded. The main heap is
- * WAL-logged as XLOG FPI records, which are not logically decoded.
+ * While rewriting the heap for REPACK, make sure data for the TOAST
+ * table are not logically decoded. The main heap is WAL-logged as
+ * XLOG FPI records, which are not logically decoded.
*/
options |= HEAP_INSERT_NO_LOGICAL;
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 6c1461c9ef6..9b7f8cf8497 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1298,16 +1298,19 @@ CREATE VIEW pg_stat_progress_repack AS
WHEN 2 THEN 'index scanning heap'
WHEN 3 THEN 'sorting tuples'
WHEN 4 THEN 'writing new heap'
- WHEN 5 THEN 'swapping relation files'
- WHEN 6 THEN 'rebuilding index'
- WHEN 7 THEN 'performing final cleanup'
+ WHEN 5 THEN 'catch-up'
+ WHEN 6 THEN 'swapping relation files'
+ WHEN 7 THEN 'rebuilding index'
+ WHEN 8 THEN 'performing final cleanup'
END AS phase,
CAST(S.param3 AS oid) AS repack_index_relid,
S.param4 AS heap_tuples_scanned,
- S.param5 AS heap_tuples_written,
- S.param6 AS heap_blks_total,
- S.param7 AS heap_blks_scanned,
- S.param8 AS index_rebuild_count
+ S.param5 AS heap_tuples_inserted,
+ S.param6 AS heap_tuples_updated,
+ S.param7 AS heap_tuples_deleted,
+ S.param8 AS heap_blks_total,
+ S.param9 AS heap_blks_scanned,
+ S.param10 AS index_rebuild_count
FROM pg_stat_get_progress_info('REPACK') AS S
LEFT JOIN pg_database D ON S.datid = D.oid;
@@ -1325,7 +1328,7 @@ CREATE VIEW pg_stat_progress_cluster AS
phase,
repack_index_relid AS cluster_index_relid,
heap_tuples_scanned,
- heap_tuples_written,
+ heap_tuples_inserted + heap_tuples_updated AS heap_tuples_written,
heap_blks_total,
heap_blks_scanned,
index_rebuild_count
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index a2d72ce494d..569705abc81 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -1,8 +1,23 @@
/*-------------------------------------------------------------------------
*
* cluster.c
- * CLUSTER a table on an index. This is now also used for VACUUM FULL and
- * REPACK.
+ * Implementation of REPACK [CONCURRENTLY], also known as CLUSTER and
+ * VACUUM FULL.
+ *
+ * There are two somewhat different ways to rewrite a table. In non-
+ * concurrent mode, it's easy: take AccessExclusiveLock, create a new
+ * transient relation, copy the tuples over to the relfilenode of the new
+ * relation, swap the relfilenodes, then drop the old relation.
+ *
+ * In concurrent mode, we lock the table with only ShareUpdateExclusiveLock,
+ * then do an initial copy as above. However, while the tuples are being
+ * copied, concurrent transactions could modify the table. To cope with those
+ * changes, we rely on logical decoding to obtain them from WAL. The changes
+ * are accumulated in a tuplestore. Once the initial copy is complete, we
+ * read the changes from the tuplestore and re-apply them on the new heap.
+ * Then we upgrade our ShareUpdateExclusiveLock to AccessExclusiveLock and
+ * swap the relfilenodes. This way, the time we hold a strong lock on the
+ * table is much reduced, and the bloat is eliminated.
*
* There is hardly anything left of Paul Brown's original implementation...
*
@@ -26,6 +41,10 @@
#include "access/toast_internals.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xlog_internal.h"
+#include "access/xloginsert.h"
+#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/heap.h"
@@ -33,6 +52,7 @@
#include "catalog/namespace.h"
#include "catalog/objectaccess.h"
#include "catalog/pg_am.h"
+#include "catalog/pg_control.h"
#include "catalog/pg_inherits.h"
#include "catalog/toasting.h"
#include "commands/cluster.h"
@@ -40,15 +60,21 @@
#include "commands/progress.h"
#include "commands/tablecmds.h"
#include "commands/vacuum.h"
+#include "executor/executor.h"
#include "miscadmin.h"
#include "optimizer/optimizer.h"
#include "pgstat.h"
+#include "replication/decode.h"
+#include "replication/logical.h"
+#include "replication/snapbuild.h"
#include "storage/bufmgr.h"
+#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "utils/acl.h"
#include "utils/fmgroids.h"
#include "utils/guc.h"
+#include "utils/injection_point.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
@@ -68,12 +94,62 @@ typedef struct
Oid indexOid;
} RelToCluster;
+/*
+ * The following definitions are used for concurrent processing.
+ */
+
+/*
+ * The locators are used to avoid logical decoding of data that we do not need
+ * for our table.
+ */
+RelFileLocator repacked_rel_locator = {.relNumber = InvalidOid};
+RelFileLocator repacked_rel_toast_locator = {.relNumber = InvalidOid};
+
+/*
+ * Everything we need to call ExecInsertIndexTuples().
+ */
+typedef struct IndexInsertState
+{
+ ResultRelInfo *rri;
+ EState *estate;
+} IndexInsertState;
+
+/* The WAL segment being decoded. */
+static XLogSegNo repack_current_segment = 0;
+
+/*
+ * Information needed to apply concurrent data changes.
+ */
+typedef struct ChangeDest
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ /*
+ * The following is needed to find the existing tuple if the change is
+ * UPDATE or DELETE. 'ident_key' should have all the fields except for
+ * 'sk_argument' initialized.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+ int ident_key_nentries;
+
+ /* Needed to update indexes of rel_dst. */
+ IndexInsertState *iistate;
+} ChangeDest;
+
static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap,
- Oid indexOid, Oid userid, int options);
-static void rebuild_relation(Relation OldHeap, Relation index, bool verbose);
+ Oid indexOid, Oid userid, LOCKMODE lmode,
+ int options);
+static void check_repack_concurrently_requirements(Relation rel);
+static void rebuild_relation(Relation OldHeap, Relation index, bool verbose,
+ bool concurrent);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- bool verbose, bool *pSwapToastByContent,
- TransactionId *pFreezeXid, MultiXactId *pCutoffMulti);
+ Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
+ bool verbose,
+ bool *pSwapToastByContent,
+ TransactionId *pFreezeXid,
+ MultiXactId *pCutoffMulti);
static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
MemoryContext permcxt);
static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -81,13 +157,51 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
MemoryContext permcxt);
static bool cluster_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
+
+static void begin_concurrent_repack(Relation rel);
+static void end_concurrent_repack(void);
+static LogicalDecodingContext *setup_logical_decoding(Oid relid);
+static HeapTuple get_changed_tuple(char *change);
+static void apply_concurrent_changes(RepackDecodingState *dstate,
+ ChangeDest *dest);
+static void apply_concurrent_insert(Relation rel, HeapTuple tup,
+ IndexInsertState *iistate,
+ TupleTableSlot *index_slot);
+static void apply_concurrent_update(Relation rel, HeapTuple tup,
+ HeapTuple tup_target,
+ IndexInsertState *iistate,
+ TupleTableSlot *index_slot);
+static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
+static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
+ HeapTuple tup_key,
+ TupleTableSlot *ident_slot);
+static void process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
+ XLogRecPtr end_of_wal,
+ ChangeDest *dest);
+static IndexInsertState *get_index_insert_state(Relation relation,
+ Oid ident_index_id,
+ Relation *ident_index_p);
+static ScanKey build_identity_key(Oid ident_idx_oid, Relation rel_src,
+ int *nentries);
+static void free_index_insert_state(IndexInsertState *iistate);
+static void cleanup_logical_decoding(LogicalDecodingContext *ctx);
+static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
+ Relation cl_index,
+ LogicalDecodingContext *decoding_ctx,
+ TransactionId frozenXid,
+ MultiXactId cutoffMulti);
+static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes);
static Relation process_single_relation(RepackStmt *stmt,
+ LOCKMODE lockmode,
+ bool isTopLevel,
ClusterParams *params);
static Oid determine_clustered_index(Relation rel, bool usingindex,
const char *indexname);
static const char *RepackCommandAsString(RepackCommand cmd);
+#define REPL_PLUGIN_NAME "pgoutput_repack"
+
/*
* The repack code allows for processing multiple tables at once. Because
* of this, we cannot just run everything on a single transaction, or we
@@ -117,6 +231,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
ClusterParams params = {0};
Relation rel = NULL;
MemoryContext repack_context;
+ LOCKMODE lockmode;
List *rtcs;
/* Parse option list */
@@ -127,6 +242,16 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
else if (strcmp(opt->defname, "analyze") == 0 ||
strcmp(opt->defname, "analyse") == 0)
params.options |= defGetBoolean(opt) ? CLUOPT_ANALYZE : 0;
+ else if (strcmp(opt->defname, "concurrently") == 0 &&
+ defGetBoolean(opt))
+ {
+ if (stmt->command != REPACK_COMMAND_REPACK)
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("CONCURRENTLY option not supported for %s",
+ RepackCommandAsString(stmt->command)));
+ params.options |= CLUOPT_CONCURRENT;
+ }
else
ereport(ERROR,
errcode(ERRCODE_SYNTAX_ERROR),
@@ -136,13 +261,25 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
parser_errposition(pstate, opt->location));
}
+ /*
+ * Determine the lock mode expected by cluster_rel().
+ *
+ * In the exclusive case, we obtain AccessExclusiveLock right away to
+ * avoid lock-upgrade hazard in the single-transaction case. In the
+ * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end
+ * of processing, supposedly for very short time. Until then, we'll have
+ * to unlock the relation temporarily, so there's no lock-upgrade hazard.
+ */
+ lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ?
+ AccessExclusiveLock : ShareUpdateExclusiveLock;
+
/*
* 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.
*/
if (stmt->relation != NULL)
{
- rel = process_single_relation(stmt, ¶ms);
+ rel = process_single_relation(stmt, lockmode, isTopLevel, ¶ms);
if (rel == NULL)
return; /* all done */
}
@@ -157,10 +294,29 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
errmsg("cannot %s multiple tables", "REPACK (ANALYZE)"));
/*
- * By here, we know we are in a multi-table situation. In order to avoid
- * holding locks for too long, we want to process each table in its own
- * transaction. This forces us to disallow running inside a user
- * transaction block.
+ * By here, we know we are in a multi-table situation.
+ *
+ * Concurrent processing is currently considered rather special (e.g. in
+ * terms of resources consumed) so it is not performed in bulk.
+ */
+ if (params.options & CLUOPT_CONCURRENT)
+ {
+ if (rel != NULL)
+ {
+ Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
+ ereport(ERROR,
+ errmsg("REPACK CONCURRENTLY not supported for partitioned tables"),
+ errhint("Consider running the command for individual partitions."));
+ }
+ else
+ ereport(ERROR,
+ errmsg("REPACK CONCURRENTLY requires explicit table name"));
+ }
+
+ /*
+ * In order to avoid holding locks for too long, we want to process each
+ * table in its own transaction. This forces us to disallow running
+ * inside a user transaction block.
*/
PreventInTransactionBlock(isTopLevel, RepackCommandAsString(stmt->command));
@@ -243,7 +399,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
* Open the target table, coping with the case where it has been
* dropped.
*/
- rel = try_table_open(rtc->tableOid, AccessExclusiveLock);
+ rel = try_table_open(rtc->tableOid, lockmode);
if (rel == NULL)
{
CommitTransactionCommand();
@@ -254,7 +410,7 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
PushActiveSnapshot(GetTransactionSnapshot());
/* Process this table */
- cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms);
+ cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms, isTopLevel);
/* cluster_rel closes the relation, but keeps lock */
PopActiveSnapshot();
@@ -283,22 +439,53 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel)
* 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.)
+ *
* 'cmd' indicates which command is being executed, to be used for error
* messages.
*/
void
cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
- ClusterParams *params)
+ ClusterParams *params, bool isTopLevel)
{
Oid tableOid = RelationGetRelid(OldHeap);
+ Relation index;
+ LOCKMODE lmode;
Oid save_userid;
int save_sec_context;
int save_nestlevel;
bool verbose = ((params->options & CLUOPT_VERBOSE) != 0);
bool recheck = ((params->options & CLUOPT_RECHECK) != 0);
- Relation index;
+ bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0);
+
+ /*
+ * The lock mode is AccessExclusiveLock for normal processing and
+ * ShareUpdateExclusiveLock for concurrent processing (so that SELECT,
+ * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be
+ * called concurrently for the same relation).
+ */
+ lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock;
- Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false));
+ /* There are specific requirements on concurrent processing. */
+ if (concurrent)
+ {
+ /*
+ * Make sure we have no XID assigned, otherwise call of
+ * setup_logical_decoding() can cause a deadlock.
+ *
+ * The existence of transaction block actually does not imply that XID
+ * was already assigned, but it very likely is. We might want to check
+ * the result of GetCurrentTransactionIdIfAny() instead, but that
+ * would be less clear from user's perspective.
+ */
+ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)");
+
+ check_repack_concurrently_requirements(OldHeap);
+ }
/* Check for user-requested abort. */
CHECK_FOR_INTERRUPTS();
@@ -324,10 +511,13 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* If this is a single-transaction CLUSTER, we can skip these tests. We
* *must* skip the one on indisclustered since it would reject an attempt
* to cluster a not-previously-clustered index.
+ *
+ * XXX move [some of] these comments to where the RECHECK flag is
+ * determined?
*/
if (recheck &&
!cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid,
- params->options))
+ lmode, params->options))
goto out;
/*
@@ -342,6 +532,12 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
errmsg("cannot run %s on a shared catalog",
RepackCommandAsString(cmd)));
+ /*
+ * The CONCURRENTLY case should have been rejected earlier because it does
+ * not support system catalogs.
+ */
+ Assert(!(OldHeap->rd_rel->relisshared && concurrent));
+
/*
* Don't process temp tables of other backends ... their local buffer
* manager is not going to cope.
@@ -362,7 +558,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if (OidIsValid(indexOid))
{
/* verify the index is good and lock it */
- check_index_is_clusterable(OldHeap, indexOid, AccessExclusiveLock);
+ check_index_is_clusterable(OldHeap, indexOid, lmode);
/* also open it */
index = index_open(indexOid, NoLock);
}
@@ -397,7 +593,9 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if (OldHeap->rd_rel->relkind == RELKIND_MATVIEW &&
!RelationIsPopulated(OldHeap))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ if (index)
+ index_close(index, lmode);
+ relation_close(OldHeap, lmode);
goto out;
}
@@ -410,11 +608,34 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* invalid, because we move tuples around. Promote them to relation
* locks. Predicate locks on indexes will be promoted when they are
* reindexed.
+ *
+ * During concurrent processing, the heap as well as its indexes stay in
+ * operation, so we postpone this step until they are locked using
+ * AccessExclusiveLock near the end of the processing.
*/
- TransferPredicateLocksToHeapRelation(OldHeap);
+ if (!concurrent)
+ TransferPredicateLocksToHeapRelation(OldHeap);
/* rebuild_relation does all the dirty work */
- rebuild_relation(OldHeap, index, verbose);
+ PG_TRY();
+ {
+ /*
+ * For concurrent processing, make sure that our logical decoding
+ * ignores data changes of other tables than the one we are
+ * processing.
+ */
+ if (concurrent)
+ begin_concurrent_repack(OldHeap);
+
+ rebuild_relation(OldHeap, index, verbose, concurrent);
+ }
+ PG_FINALLY();
+ {
+ if (concurrent)
+ end_concurrent_repack();
+ }
+ PG_END_TRY();
+
/* rebuild_relation closes OldHeap, and index if valid */
out:
@@ -433,14 +654,14 @@ out:
*/
static bool
cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
- Oid userid, int options)
+ Oid userid, LOCKMODE lmode, int options)
{
Oid tableOid = RelationGetRelid(OldHeap);
/* Check that the user still has privileges for the relation */
if (!cluster_is_permitted_for_relation(cmd, tableOid, userid))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -454,7 +675,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
*/
if (RELATION_IS_OTHER_TEMP(OldHeap))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -465,7 +686,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
*/
if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid)))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
@@ -476,7 +697,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
if ((options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
!get_index_isclustered(indexOid))
{
- relation_close(OldHeap, AccessExclusiveLock);
+ relation_close(OldHeap, lmode);
return false;
}
}
@@ -488,7 +709,7 @@ cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid,
* Verify that the specified heap and index are valid to cluster on
*
* Side effect: obtains lock on the index. The caller may
- * in some cases already have AccessExclusiveLock on the table, but
+ * in some cases already have a lock of the same strength on the table, but
* not in all cases so we can't rely on the table-level lock for
* protection here.
*/
@@ -617,18 +838,87 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
table_close(pg_index, RowExclusiveLock);
}
+/*
+ * Check if the CONCURRENTLY option is legal for the relation.
+ */
+static void
+check_repack_concurrently_requirements(Relation rel)
+{
+ char relpersistence,
+ replident;
+ Oid ident_idx;
+
+ /* Data changes in system relations are not logically decoded. */
+ if (IsCatalogRelation(rel))
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is not supported for catalog relations.")));
+
+ /*
+ * reorderbuffer.c does not seem to handle processing of TOAST relation
+ * alone.
+ */
+ if (IsToastRelation(rel))
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is not supported for TOAST relations, unless the main relation is repacked too.")));
+
+ relpersistence = rel->rd_rel->relpersistence;
+ if (relpersistence != RELPERSISTENCE_PERMANENT)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("REPACK CONCURRENTLY is only allowed for permanent relations.")));
+
+ /* With NOTHING, WAL does not contain the old tuple. */
+ replident = rel->rd_rel->relreplident;
+ if (replident == REPLICA_IDENTITY_NOTHING)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot repack relation \"%s\"",
+ RelationGetRelationName(rel)),
+ errhint("Relation \"%s\" has insufficient replication identity.",
+ RelationGetRelationName(rel))));
+
+ /*
+ * Identity index is not set if the replica identity is FULL, but PK might
+ * exist in such a case.
+ */
+ ident_idx = RelationGetReplicaIndex(rel);
+ if (!OidIsValid(ident_idx) && OidIsValid(rel->rd_pkindex))
+ ident_idx = rel->rd_pkindex;
+ if (!OidIsValid(ident_idx))
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot process relation \"%s\"",
+ RelationGetRelationName(rel)),
+ (errhint("Relation \"%s\" has no identity index.",
+ RelationGetRelationName(rel)))));
+}
+
+
/*
* rebuild_relation: rebuild an existing relation in index or physical order
*
- * OldHeap: table to rebuild.
+ * OldHeap: table to rebuild. See cluster_rel() for comments on the required
+ * lock strength.
+ *
* index: index to cluster by, or NULL to rewrite in physical order.
*
- * On entry, heap and index (if one is given) must be open, and
- * AccessExclusiveLock held on them.
- * On exit, they are closed, but locks on them are not released.
+ * On entry, heap and index (if one is given) must be open, and the
+ * appropriate lock held on them -- AccessExclusiveLock for exclusive
+ * processing and ShareUpdateExclusiveLock for concurrent processing.
+ *
+ * On exit, they are closed, but still locked with AccessExclusiveLock.
+ * (The function handles the lock upgrade if 'concurrent' is true.)
*/
static void
-rebuild_relation(Relation OldHeap, Relation index, bool verbose)
+rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent)
{
Oid tableOid = RelationGetRelid(OldHeap);
Oid accessMethod = OldHeap->rd_rel->relam;
@@ -636,13 +926,38 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
Oid OIDNewHeap;
Relation NewHeap;
char relpersistence;
- bool is_system_catalog;
bool swap_toast_by_content;
TransactionId frozenXid;
MultiXactId cutoffMulti;
+ LogicalDecodingContext *decoding_ctx = NULL;
+ Snapshot snapshot = NULL;
+#if USE_ASSERT_CHECKING
+ LOCKMODE lmode;
+
+ lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
+
+ Assert(CheckRelationLockedByMe(OldHeap, lmode, false));
+ Assert(index == NULL || CheckRelationLockedByMe(index, lmode, false));
+#endif
+
+ if (concurrent)
+ {
+ /*
+ * Prepare to capture the concurrent data changes.
+ *
+ * Note that this call waits 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 its still eligible for REPACK
+ * CONCURRENTLY.
+ */
+ decoding_ctx = setup_logical_decoding(tableOid);
- Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false) &&
- (index == NULL || CheckRelationLockedByMe(index, AccessExclusiveLock, false)));
+ snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
+ PushActiveSnapshot(snapshot);
+ }
/* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */
if (index != NULL)
@@ -650,7 +965,6 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
/* Remember info about rel before closing OldHeap */
relpersistence = OldHeap->rd_rel->relpersistence;
- is_system_catalog = IsSystemRelation(OldHeap);
/*
* Create the transient table that will receive the re-ordered data.
@@ -666,30 +980,54 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose)
NewHeap = table_open(OIDNewHeap, NoLock);
/* Copy the heap data into the new table in the desired order */
- copy_table_data(NewHeap, OldHeap, index, verbose,
+ copy_table_data(NewHeap, OldHeap, index, snapshot, decoding_ctx, verbose,
&swap_toast_by_content, &frozenXid, &cutoffMulti);
+ /* The historic snapshot won't be needed anymore. */
+ if (snapshot)
+ {
+ PopActiveSnapshot();
+ UpdateActiveSnapshotCommandId();
+ }
- /* Close relcache entries, but keep lock until transaction commit */
- table_close(OldHeap, NoLock);
- if (index)
- index_close(index, NoLock);
+ if (concurrent)
+ {
+ Assert(!swap_toast_by_content);
+ rebuild_relation_finish_concurrent(NewHeap, OldHeap, index,
+ decoding_ctx,
+ frozenXid, cutoffMulti);
- /*
- * Close the new relation so it can be dropped as soon as the storage is
- * swapped. The relation is not visible to others, so no need to unlock it
- * explicitly.
- */
- table_close(NewHeap, NoLock);
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
- /*
- * Swap the physical files of the target and transient tables, then
- * rebuild the target's indexes and throw away the transient table.
- */
- finish_heap_swap(tableOid, OIDNewHeap, is_system_catalog,
- swap_toast_by_content, false, true,
- frozenXid, cutoffMulti,
- relpersistence);
+ /* Done with decoding. */
+ cleanup_logical_decoding(decoding_ctx);
+ }
+ else
+ {
+ bool is_system_catalog = IsSystemRelation(OldHeap);
+
+ /* Close relcache entries, but keep lock until transaction commit */
+ table_close(OldHeap, NoLock);
+ if (index)
+ index_close(index, NoLock);
+
+ /*
+ * Close the new relation so it can be dropped as soon as the storage
+ * is swapped. The relation is not visible to others, so no need to
+ * unlock it explicitly.
+ */
+ table_close(NewHeap, NoLock);
+
+ /*
+ * Swap the physical files of the target and transient tables, then
+ * rebuild the target's indexes and throw away the transient table.
+ */
+ finish_heap_swap(tableOid, OIDNewHeap, is_system_catalog,
+ swap_toast_by_content, false, true, true,
+ frozenXid, cutoffMulti,
+ relpersistence);
+ }
}
@@ -824,15 +1162,19 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
/*
* Do the physical copying of table data.
*
+ * 'snapshot' and 'decoding_ctx': see table_relation_copy_for_cluster(). Pass
+ * iff concurrent processing is required.
+ *
* There are three output parameters:
* *pSwapToastByContent is set true if toast tables must be swapped by content.
* *pFreezeXid receives the TransactionId used as freeze cutoff point.
* *pCutoffMulti receives the MultiXactId used as a cutoff point.
*/
static void
-copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verbose,
- bool *pSwapToastByContent, TransactionId *pFreezeXid,
- MultiXactId *pCutoffMulti)
+copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
+ Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
+ bool verbose, bool *pSwapToastByContent,
+ TransactionId *pFreezeXid, MultiXactId *pCutoffMulti)
{
Relation relRelation;
HeapTuple reltup;
@@ -849,6 +1191,10 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
int elevel = verbose ? INFO : DEBUG2;
PGRUsage ru0;
char *nspname;
+ bool concurrent = snapshot != NULL;
+ LOCKMODE lmode;
+
+ lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
pg_rusage_init(&ru0);
@@ -877,7 +1223,7 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* will be held till end of transaction.
*/
if (OldHeap->rd_rel->reltoastrelid)
- LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, lmode);
/*
* If both tables have TOAST tables, perform toast swap by content. It is
@@ -886,7 +1232,8 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* swap by links. This is okay because swap by content is only essential
* for system catalogs, and we don't support schema changes for them.
*/
- if (OldHeap->rd_rel->reltoastrelid && NewHeap->rd_rel->reltoastrelid)
+ if (OldHeap->rd_rel->reltoastrelid && NewHeap->rd_rel->reltoastrelid &&
+ !concurrent)
{
*pSwapToastByContent = true;
@@ -907,6 +1254,10 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* follow the toast pointers to the wrong place. (It would actually
* work for values copied over from the old toast table, but not for
* any values that we toast which were previously not toasted.)
+ *
+ * This would not work with CONCURRENTLY because we may need to delete
+ * TOASTed tuples from the new heap. With this hack, we'd delete them
+ * from the old heap.
*/
NewHeap->rd_toastoid = OldHeap->rd_rel->reltoastrelid;
}
@@ -982,7 +1333,9 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
* values (e.g. because the AM doesn't use freezing).
*/
table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort,
- cutoffs.OldestXmin, &cutoffs.FreezeLimit,
+ cutoffs.OldestXmin, snapshot,
+ decoding_ctx,
+ &cutoffs.FreezeLimit,
&cutoffs.MultiXactCutoff,
&num_tuples, &tups_vacuumed,
&tups_recently_dead);
@@ -991,7 +1344,11 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verb
*pFreezeXid = cutoffs.FreezeLimit;
*pCutoffMulti = cutoffs.MultiXactCutoff;
- /* Reset rd_toastoid just to be tidy --- it shouldn't be looked at again */
+ /*
+ * Reset rd_toastoid just to be tidy --- it shouldn't be looked at again.
+ * In the CONCURRENTLY case, we need to set it again before applying the
+ * concurrent changes.
+ */
NewHeap->rd_toastoid = InvalidOid;
num_pages = RelationGetNumberOfBlocks(NewHeap);
@@ -1449,14 +1806,13 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
bool swap_toast_by_content,
bool check_constraints,
bool is_internal,
+ bool reindex,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence)
{
ObjectAddress object;
Oid mapped_tables[4];
- int reindex_flags;
- ReindexParams reindex_params = {0};
int i;
/* Report that we are now swapping relation files */
@@ -1482,39 +1838,47 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
if (is_system_catalog)
CacheInvalidateCatalog(OIDOldHeap);
- /*
- * Rebuild each index on the relation (but not the toast table, which is
- * all-new at this point). It is important to do this before the DROP
- * step because if we are processing a system catalog that will be used
- * during DROP, we want to have its indexes available. There is no
- * advantage to the other order anyway because this is all transactional,
- * so no chance to reclaim disk space before commit. We do not need a
- * final CommandCounterIncrement() because reindex_relation does it.
- *
- * Note: because index_build is called via reindex_relation, it will never
- * set indcheckxmin true for the indexes. This is OK even though in some
- * sense we are building new indexes rather than rebuilding existing ones,
- * because the new heap won't contain any HOT chains at all, let alone
- * broken ones, so it can't be necessary to set indcheckxmin.
- */
- reindex_flags = REINDEX_REL_SUPPRESS_INDEX_USE;
- if (check_constraints)
- reindex_flags |= REINDEX_REL_CHECK_CONSTRAINTS;
+ if (reindex)
+ {
+ int reindex_flags;
+ ReindexParams reindex_params = {0};
- /*
- * Ensure that the indexes have the same persistence as the parent
- * relation.
- */
- if (newrelpersistence == RELPERSISTENCE_UNLOGGED)
- reindex_flags |= REINDEX_REL_FORCE_INDEXES_UNLOGGED;
- else if (newrelpersistence == RELPERSISTENCE_PERMANENT)
- reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
+ /*
+ * Rebuild each index on the relation (but not the toast table, which
+ * is all-new at this point). It is important to do this before the
+ * DROP step because if we are processing a system catalog that will
+ * be used during DROP, we want to have its indexes available. There
+ * is no advantage to the other order anyway because this is all
+ * transactional, so no chance to reclaim disk space before commit. We
+ * do not need a final CommandCounterIncrement() because
+ * reindex_relation does it.
+ *
+ * Note: because index_build is called via reindex_relation, it will
+ * never set indcheckxmin true for the indexes. This is OK even
+ * though in some sense we are building new indexes rather than
+ * rebuilding existing ones, because the new heap won't contain any
+ * HOT chains at all, let alone broken ones, so it can't be necessary
+ * to set indcheckxmin.
+ */
+ reindex_flags = REINDEX_REL_SUPPRESS_INDEX_USE;
+ if (check_constraints)
+ reindex_flags |= REINDEX_REL_CHECK_CONSTRAINTS;
- /* Report that we are now reindexing relations */
- pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
- PROGRESS_REPACK_PHASE_REBUILD_INDEX);
+ /*
+ * Ensure that the indexes have the same persistence as the parent
+ * relation.
+ */
+ if (newrelpersistence == RELPERSISTENCE_UNLOGGED)
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_UNLOGGED;
+ else if (newrelpersistence == RELPERSISTENCE_PERMANENT)
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
+
+ /* Report that we are now reindexing relations */
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_REBUILD_INDEX);
- reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params);
+ reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params);
+ }
/* Report that we are now doing clean up */
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
@@ -1558,6 +1922,17 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
object.objectId = OIDNewHeap;
object.objectSubId = 0;
+ if (!reindex)
+ {
+ /*
+ * Make sure the changes in pg_class are visible. This is especially
+ * important if !swap_toast_by_content, so that the correct TOAST
+ * relation is dropped. (reindex_relation() above did not help in this
+ * case))
+ */
+ CommandCounterIncrement();
+ }
+
/*
* The new relation is local to our transaction and we know nothing
* depends on it, so DROP_RESTRICT should be OK.
@@ -1597,7 +1972,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
/* Get the associated valid index to be renamed */
toastidx = toast_get_valid_index(newrel->rd_rel->reltoastrelid,
- NoLock);
+ AccessExclusiveLock);
/* rename the toast table ... */
snprintf(NewToastName, NAMEDATALEN, "pg_toast_%u",
@@ -1857,7 +2232,8 @@ cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid)
* case, if an index name is given, it's up to the caller to resolve it.
*/
static Relation
-process_single_relation(RepackStmt *stmt, ClusterParams *params)
+process_single_relation(RepackStmt *stmt, LOCKMODE lockmode, bool isTopLevel,
+ ClusterParams *params)
{
Relation rel;
Oid tableOid;
@@ -1866,13 +2242,9 @@ process_single_relation(RepackStmt *stmt, ClusterParams *params)
Assert(stmt->command == REPACK_COMMAND_CLUSTER ||
stmt->command == REPACK_COMMAND_REPACK);
- /*
- * Find, lock, and check permissions on the table. We obtain
- * AccessExclusiveLock right away to avoid lock-upgrade hazard in the
- * single-transaction case.
- */
+ /* Find, lock, and check permissions on the table. */
tableOid = RangeVarGetRelidExtended(stmt->relation->relation,
- AccessExclusiveLock,
+ lockmode,
0,
RangeVarCallbackMaintainsTable,
NULL);
@@ -1904,13 +2276,14 @@ process_single_relation(RepackStmt *stmt, ClusterParams *params)
return rel;
else
{
- Oid indexOid;
+ Oid indexOid = InvalidOid;
indexOid = determine_clustered_index(rel, stmt->usingindex,
stmt->indexname);
if (OidIsValid(indexOid))
- check_index_is_clusterable(rel, indexOid, AccessExclusiveLock);
- cluster_rel(stmt->command, rel, indexOid, params);
+ check_index_is_clusterable(rel, indexOid, lockmode);
+
+ cluster_rel(stmt->command, rel, indexOid, params, isTopLevel);
/* Do an analyze, if requested */
if (params->options & CLUOPT_ANALYZE)
@@ -1993,3 +2366,1019 @@ RepackCommandAsString(RepackCommand cmd)
}
return "???";
}
+
+
+/*
+ * Call this function before REPACK CONCURRENTLY starts to setup logical
+ * decoding. It makes sure that other users of the table put enough
+ * information into WAL.
+ *
+ * The point is that at various places we expect that the table we're
+ * processing is treated like a system catalog. For example, we need to be
+ * able to scan it using a "historic snapshot" anytime during the processing
+ * (as opposed to scanning only at the start point of the decoding, as logical
+ * replication does during initial table synchronization), in order to apply
+ * concurrent UPDATE / DELETE commands.
+ *
+ * Note that TOAST table needs no attention here as it's not scanned using
+ * historic snapshot.
+ */
+static void
+begin_concurrent_repack(Relation rel)
+{
+ Oid toastrelid;
+
+ /*
+ * Avoid logical decoding of other relations by this backend. The lock we
+ * have guarantees that the actual locator cannot be changed concurrently:
+ * TRUNCATE needs AccessExclusiveLock.
+ */
+ Assert(CheckRelationLockedByMe(rel, ShareUpdateExclusiveLock, false));
+ repacked_rel_locator = rel->rd_locator;
+ toastrelid = rel->rd_rel->reltoastrelid;
+ if (OidIsValid(toastrelid))
+ {
+ Relation toastrel;
+
+ /* Avoid logical decoding of other TOAST relations. */
+ toastrel = table_open(toastrelid, AccessShareLock);
+ repacked_rel_toast_locator = toastrel->rd_locator;
+ table_close(toastrel, AccessShareLock);
+ }
+}
+
+/*
+ * Call this when done with REPACK CONCURRENTLY.
+ */
+static void
+end_concurrent_repack(void)
+{
+ /*
+ * Restore normal function of (future) logical decoding for this backend.
+ */
+ repacked_rel_locator.relNumber = InvalidOid;
+ repacked_rel_toast_locator.relNumber = InvalidOid;
+}
+
+/*
+ * This function is much like pg_create_logical_replication_slot() except that
+ * the new slot is neither released (if anyone else could read changes from
+ * our slot, we could miss changes other backends do while we copy the
+ * existing data into temporary table), nor persisted (it's easier to handle
+ * crash by restarting all the work from scratch).
+ */
+static LogicalDecodingContext *
+setup_logical_decoding(Oid relid)
+{
+ Relation rel;
+ TupleDesc tupdesc;
+ LogicalDecodingContext *ctx;
+ RepackDecodingState *dstate = palloc0_object(RepackDecodingState);
+
+ /*
+ * REPACK CONCURRENTLY is not allowed in a transaction block, so this
+ * should never fire.
+ */
+ Assert(!TransactionIdIsValid(GetTopTransactionIdIfAny()));
+
+ /*
+ * A single backend should not execute multiple REPACK commands at a time,
+ * so use PID to make the slot unique.
+ */
+ snprintf(NameStr(dstate->slotname), NAMEDATALEN, "repack_%d", MyProcPid);
+
+ /*
+ * Check if we can use logical decoding.
+ */
+ CheckSlotPermissions();
+ CheckLogicalDecodingRequirements();
+
+ /* RS_TEMPORARY so that the slot gets cleaned up on ERROR. */
+ ReplicationSlotCreate(NameStr(dstate->slotname), true, RS_TEMPORARY,
+ false, false, false);
+
+ /*
+ * Neither prepare_write nor do_write callback nor update_progress is
+ * useful for us.
+ */
+ ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME,
+ NIL,
+ true,
+ InvalidXLogRecPtr,
+ XL_ROUTINE(.page_read = read_local_xlog_page,
+ .segment_open = wal_segment_open,
+ .segment_close = wal_segment_close),
+ NULL, NULL, NULL);
+
+ /*
+ * We don't have control on setting fast_forward, so at least check it.
+ */
+ Assert(!ctx->fast_forward);
+
+ DecodingContextFindStartpoint(ctx);
+
+ /* Some WAL records should have been read. */
+ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr);
+
+ XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment,
+ wal_segment_size);
+
+ /*
+ * Setup structures to store decoded changes.
+ */
+ dstate->relid = relid;
+ dstate->tstore = tuplestore_begin_heap(false, false,
+ maintenance_work_mem);
+
+ /* Caller should already have the table locked. */
+ rel = table_open(relid, NoLock);
+ tupdesc = CreateTupleDescCopy(RelationGetDescr(rel));
+ dstate->tupdesc = tupdesc;
+ table_close(rel, NoLock);
+
+ /* Initialize the descriptor to store the changes ... */
+ dstate->tupdesc_change = CreateTemplateTupleDesc(1);
+
+ TupleDescInitEntry(dstate->tupdesc_change, 1, NULL, BYTEAOID, -1, 0);
+ /* ... as well as the corresponding slot. */
+ dstate->tsslot = MakeSingleTupleTableSlot(dstate->tupdesc_change,
+ &TTSOpsMinimalTuple);
+
+ dstate->resowner = ResourceOwnerCreate(CurrentResourceOwner,
+ "logical decoding");
+
+ ctx->output_writer_private = dstate;
+ return ctx;
+}
+
+/*
+ * Retrieve tuple from ConcurrentChange structure.
+ *
+ * The input data starts with the structure but it might not be appropriately
+ * aligned.
+ */
+static HeapTuple
+get_changed_tuple(char *change)
+{
+ HeapTupleData tup_data;
+ HeapTuple result;
+ char *src;
+
+ /*
+ * Ensure alignment before accessing the fields. (This is why we can't use
+ * heap_copytuple() instead of this function.)
+ */
+ src = change + offsetof(ConcurrentChange, tup_data);
+ memcpy(&tup_data, src, sizeof(HeapTupleData));
+
+ result = (HeapTuple) palloc(HEAPTUPLESIZE + tup_data.t_len);
+ memcpy(result, &tup_data, sizeof(HeapTupleData));
+ result->t_data = (HeapTupleHeader) ((char *) result + HEAPTUPLESIZE);
+ src = change + SizeOfConcurrentChange;
+ memcpy(result->t_data, src, result->t_len);
+
+ return result;
+}
+
+/*
+ * Decode logical changes from the WAL sequence up to end_of_wal.
+ */
+void
+repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
+ XLogRecPtr end_of_wal)
+{
+ RepackDecodingState *dstate;
+ ResourceOwner resowner_old;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+ resowner_old = CurrentResourceOwner;
+ CurrentResourceOwner = dstate->resowner;
+
+ PG_TRY();
+ {
+ while (ctx->reader->EndRecPtr < end_of_wal)
+ {
+ XLogRecord *record;
+ XLogSegNo segno_new;
+ char *errm = NULL;
+ XLogRecPtr end_lsn;
+
+ record = XLogReadRecord(ctx->reader, &errm);
+ if (errm)
+ elog(ERROR, "%s", errm);
+
+ if (record != NULL)
+ LogicalDecodingProcessRecord(ctx, ctx->reader);
+
+ /*
+ * If WAL segment boundary has been crossed, inform the decoding
+ * system that the catalog_xmin can advance. (We can confirm more
+ * often, but a filling a single WAL segment should not take much
+ * time.)
+ */
+ end_lsn = ctx->reader->EndRecPtr;
+ XLByteToSeg(end_lsn, segno_new, wal_segment_size);
+ if (segno_new != repack_current_segment)
+ {
+ LogicalConfirmReceivedLocation(end_lsn);
+ elog(DEBUG1, "REPACK: confirmed receive location %X/%X",
+ (uint32) (end_lsn >> 32), (uint32) end_lsn);
+ repack_current_segment = segno_new;
+ }
+
+ CHECK_FOR_INTERRUPTS();
+ }
+ InvalidateSystemCaches();
+ CurrentResourceOwner = resowner_old;
+ }
+ PG_CATCH();
+ {
+ /* clear all timetravel entries */
+ InvalidateSystemCaches();
+ CurrentResourceOwner = resowner_old;
+ PG_RE_THROW();
+ }
+ PG_END_TRY();
+}
+
+/*
+ * Apply changes stored in 'file'.
+ */
+static void
+apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
+{
+ Relation rel = dest->rel;
+ TupleTableSlot *index_slot,
+ *ident_slot;
+ HeapTuple tup_old = NULL;
+
+ if (dstate->nchanges == 0)
+ return;
+
+ /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
+ index_slot = MakeSingleTupleTableSlot(dstate->tupdesc, &TTSOpsHeapTuple);
+
+ /* A slot to fetch tuples from identity index. */
+ ident_slot = table_slot_create(rel, NULL);
+
+ while (tuplestore_gettupleslot(dstate->tstore, true, false,
+ dstate->tsslot))
+ {
+ bool shouldFree;
+ HeapTuple tup_change,
+ tup,
+ tup_exist;
+ char *change_raw,
+ *src;
+ ConcurrentChange change;
+ bool isnull[1];
+ Datum values[1];
+
+ CHECK_FOR_INTERRUPTS();
+
+ /* Get the change from the single-column tuple. */
+ tup_change = ExecFetchSlotHeapTuple(dstate->tsslot, false, &shouldFree);
+ heap_deform_tuple(tup_change, dstate->tupdesc_change, values, isnull);
+ Assert(!isnull[0]);
+
+ /* Make sure we access aligned data. */
+ change_raw = (char *) DatumGetByteaP(values[0]);
+ src = (char *) VARDATA(change_raw);
+ memcpy(&change, src, SizeOfConcurrentChange);
+
+ /*
+ * Extract the tuple from the change. The tuple is copied here because
+ * it might be assigned to 'tup_old', in which case it needs to
+ * survive into the next iteration.
+ */
+ tup = get_changed_tuple(src);
+
+ if (change.kind == CHANGE_UPDATE_OLD)
+ {
+ Assert(tup_old == NULL);
+ tup_old = tup;
+ }
+ else if (change.kind == CHANGE_INSERT)
+ {
+ Assert(tup_old == NULL);
+
+ apply_concurrent_insert(rel, tup, dest->iistate, index_slot);
+
+ pfree(tup);
+ }
+ else if (change.kind == CHANGE_UPDATE_NEW ||
+ change.kind == CHANGE_DELETE)
+ {
+ HeapTuple tup_key;
+
+ if (change.kind == CHANGE_UPDATE_NEW)
+ {
+ tup_key = tup_old != NULL ? tup_old : tup;
+ }
+ else
+ {
+ Assert(tup_old == NULL);
+ tup_key = tup;
+ }
+
+ /*
+ * Find the tuple to be updated or deleted.
+ */
+ tup_exist = find_target_tuple(rel, dest, tup_key, ident_slot);
+ if (tup_exist == NULL)
+ elog(ERROR, "failed to find target tuple");
+
+ if (change.kind == CHANGE_UPDATE_NEW)
+ apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
+ index_slot);
+ else
+ apply_concurrent_delete(rel, tup_exist);
+
+ if (tup_old != NULL)
+ {
+ pfree(tup_old);
+ tup_old = NULL;
+ }
+
+ pfree(tup);
+ }
+ else
+ elog(ERROR, "unrecognized kind of change: %d", change.kind);
+
+ /*
+ * If a change was applied now, increment CID for next writes and
+ * update the snapshot so it sees the changes we've applied so far.
+ */
+ if (change.kind != CHANGE_UPDATE_OLD)
+ {
+ CommandCounterIncrement();
+ UpdateActiveSnapshotCommandId();
+ }
+
+ /* TTSOpsMinimalTuple has .get_heap_tuple==NULL. */
+ Assert(shouldFree);
+ pfree(tup_change);
+ }
+
+ tuplestore_clear(dstate->tstore);
+ dstate->nchanges = 0;
+
+ /* Cleanup. */
+ ExecDropSingleTupleTableSlot(index_slot);
+ ExecDropSingleTupleTableSlot(ident_slot);
+}
+
+static void
+apply_concurrent_insert(Relation rel, HeapTuple tup, IndexInsertState *iistate,
+ TupleTableSlot *index_slot)
+{
+ List *recheck;
+
+
+ /*
+ * Like simple_heap_insert(), but make sure that the INSERT is not
+ * logically decoded - see reform_and_rewrite_tuple() for more
+ * information.
+ */
+ heap_insert(rel, tup, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL,
+ NULL);
+
+ /*
+ * Update indexes.
+ *
+ * In case functions in the index need the active snapshot and caller
+ * hasn't set one.
+ */
+ ExecStoreHeapTuple(tup, index_slot, false);
+ recheck = ExecInsertIndexTuples(iistate->rri,
+ index_slot,
+ iistate->estate,
+ false, /* update */
+ false, /* noDupErr */
+ NULL, /* specConflict */
+ NIL, /* arbiterIndexes */
+ false /* onlySummarizing */
+ );
+
+ /*
+ * If recheck is required, it must have been preformed on the source
+ * relation by now. (All the logical changes we process here are already
+ * committed.)
+ */
+ list_free(recheck);
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
+}
+
+static void
+apply_concurrent_update(Relation rel, HeapTuple tup, HeapTuple tup_target,
+ IndexInsertState *iistate, TupleTableSlot *index_slot)
+{
+ LockTupleMode lockmode;
+ TM_FailureData tmfd;
+ TU_UpdateIndexes update_indexes;
+ TM_Result res;
+ List *recheck;
+
+ /*
+ * Write the new tuple into the new heap. ('tup' gets the TID assigned
+ * here.)
+ *
+ * Do it like in simple_heap_update(), except for 'wal_logical' (and
+ * except for 'wait').
+ */
+ res = heap_update(rel, &tup_target->t_self, tup,
+ GetCurrentCommandId(true),
+ InvalidSnapshot,
+ false, /* no wait - only we are doing changes */
+ &tmfd, &lockmode, &update_indexes,
+ false /* wal_logical */ );
+ if (res != TM_Ok)
+ ereport(ERROR, (errmsg("failed to apply concurrent UPDATE")));
+
+ ExecStoreHeapTuple(tup, index_slot, false);
+
+ if (update_indexes != TU_None)
+ {
+ recheck = ExecInsertIndexTuples(iistate->rri,
+ index_slot,
+ iistate->estate,
+ true, /* update */
+ false, /* noDupErr */
+ NULL, /* specConflict */
+ NIL, /* arbiterIndexes */
+ /* onlySummarizing */
+ update_indexes == TU_Summarizing);
+ list_free(recheck);
+ }
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
+}
+
+static void
+apply_concurrent_delete(Relation rel, HeapTuple tup_target)
+{
+ TM_Result res;
+ TM_FailureData tmfd;
+
+ /*
+ * Delete tuple from the new heap.
+ *
+ * Do it like in simple_heap_delete(), except for 'wal_logical' (and
+ * except for 'wait').
+ */
+ res = heap_delete(rel, &tup_target->t_self, GetCurrentCommandId(true),
+ InvalidSnapshot, false,
+ &tmfd,
+ false, /* no wait - only we are doing changes */
+ false /* wal_logical */ );
+
+ if (res != TM_Ok)
+ ereport(ERROR, (errmsg("failed to apply concurrent DELETE")));
+
+ pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1);
+}
+
+/*
+ * Find the tuple to be updated or deleted.
+ *
+ * 'tup_key' is a tuple containing the key values for the scan.
+ *
+ * On exit,'*scan_p' contains the scan descriptor used. The caller must close
+ * it when he no longer needs the tuple returned.
+ */
+static HeapTuple
+find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
+ TupleTableSlot *ident_slot)
+{
+ Relation ident_index = dest->ident_index;
+ IndexScanDesc scan;
+ Form_pg_index ident_form;
+ int2vector *ident_indkey;
+ HeapTuple result = NULL;
+
+ /* XXX no instrumentation for now */
+ scan = index_beginscan(rel, ident_index, GetActiveSnapshot(),
+ NULL, dest->ident_key_nentries, 0);
+
+ /*
+ * Scan key is passed by caller, so it does not have to be constructed
+ * multiple times. Key entries have all fields initialized, except for
+ * sk_argument.
+ */
+ index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
+
+ /* Info needed to retrieve key values from heap tuple. */
+ ident_form = ident_index->rd_index;
+ ident_indkey = &ident_form->indkey;
+
+ /* Use the incoming tuple to finalize the scan key. */
+ for (int i = 0; i < scan->numberOfKeys; i++)
+ {
+ ScanKey entry;
+ bool isnull;
+ int16 attno_heap;
+
+ entry = &scan->keyData[i];
+ attno_heap = ident_indkey->values[i];
+ entry->sk_argument = heap_getattr(tup_key,
+ attno_heap,
+ rel->rd_att,
+ &isnull);
+ Assert(!isnull);
+ }
+ if (index_getnext_slot(scan, ForwardScanDirection, ident_slot))
+ {
+ bool shouldFree;
+
+ result = ExecFetchSlotHeapTuple(ident_slot, false, &shouldFree);
+ /* TTSOpsBufferHeapTuple has .get_heap_tuple != NULL. */
+ Assert(!shouldFree);
+ }
+ index_endscan(scan);
+
+ return result;
+}
+
+/*
+ * Decode and apply concurrent changes.
+ */
+static void
+process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
+ XLogRecPtr end_of_wal, ChangeDest *dest)
+{
+ RepackDecodingState *dstate;
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_CATCH_UP);
+
+ dstate = (RepackDecodingState *) decoding_ctx->output_writer_private;
+
+ repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+
+ if (dstate->nchanges == 0)
+ return;
+
+ apply_concurrent_changes(dstate, dest);
+}
+
+/*
+ * Initialize IndexInsertState for index specified by ident_index_id.
+ *
+ * While doing that, also return the identity index in *ident_index_p.
+ */
+static IndexInsertState *
+get_index_insert_state(Relation relation, Oid ident_index_id,
+ Relation *ident_index_p)
+{
+ EState *estate;
+ int i;
+ IndexInsertState *result;
+ Relation ident_index = NULL;
+
+ result = (IndexInsertState *) palloc0(sizeof(IndexInsertState));
+ estate = CreateExecutorState();
+
+ result->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+ InitResultRelInfo(result->rri, relation, 0, 0, 0);
+ ExecOpenIndices(result->rri, false);
+
+ /*
+ * Find the relcache entry of the identity index so that we spend no extra
+ * effort to open / close it.
+ */
+ for (i = 0; i < result->rri->ri_NumIndices; i++)
+ {
+ Relation ind_rel;
+
+ ind_rel = result->rri->ri_IndexRelationDescs[i];
+ if (ind_rel->rd_id == ident_index_id)
+ ident_index = ind_rel;
+ }
+ if (ident_index == NULL)
+ elog(ERROR, "failed to open identity index");
+
+ /* Only initialize fields needed by ExecInsertIndexTuples(). */
+ result->estate = estate;
+
+ *ident_index_p = ident_index;
+ return result;
+}
+
+/*
+ * Build scan key to process logical changes.
+ */
+static ScanKey
+build_identity_key(Oid ident_idx_oid, Relation rel_src, int *nentries)
+{
+ Relation ident_idx_rel;
+ Form_pg_index ident_idx;
+ int n,
+ i;
+ ScanKey result;
+
+ Assert(OidIsValid(ident_idx_oid));
+ ident_idx_rel = index_open(ident_idx_oid, AccessShareLock);
+ ident_idx = ident_idx_rel->rd_index;
+ n = ident_idx->indnatts;
+ result = (ScanKey) palloc(sizeof(ScanKeyData) * n);
+ for (i = 0; i < n; i++)
+ {
+ ScanKey entry;
+ int16 relattno;
+ Form_pg_attribute att;
+ Oid opfamily,
+ opcintype,
+ opno,
+ opcode;
+
+ entry = &result[i];
+ relattno = ident_idx->indkey.values[i];
+ if (relattno >= 1)
+ {
+ TupleDesc desc;
+
+ desc = rel_src->rd_att;
+ att = TupleDescAttr(desc, relattno - 1);
+ }
+ else
+ elog(ERROR, "unexpected attribute number %d in index", relattno);
+
+ opfamily = ident_idx_rel->rd_opfamily[i];
+ opcintype = ident_idx_rel->rd_opcintype[i];
+ opno = get_opfamily_member(opfamily, opcintype, opcintype,
+ BTEqualStrategyNumber);
+
+ if (!OidIsValid(opno))
+ elog(ERROR, "failed to find = operator for type %u", opcintype);
+
+ opcode = get_opcode(opno);
+ if (!OidIsValid(opcode))
+ elog(ERROR, "failed to find = operator for operator %u", opno);
+
+ /* Initialize everything but argument. */
+ ScanKeyInit(entry,
+ i + 1,
+ BTEqualStrategyNumber, opcode,
+ (Datum) NULL);
+ entry->sk_collation = att->attcollation;
+ }
+ index_close(ident_idx_rel, AccessShareLock);
+
+ *nentries = n;
+ return result;
+}
+
+static void
+free_index_insert_state(IndexInsertState *iistate)
+{
+ ExecCloseIndices(iistate->rri);
+ FreeExecutorState(iistate->estate);
+ pfree(iistate->rri);
+ pfree(iistate);
+}
+
+static void
+cleanup_logical_decoding(LogicalDecodingContext *ctx)
+{
+ RepackDecodingState *dstate;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ ExecDropSingleTupleTableSlot(dstate->tsslot);
+ FreeTupleDesc(dstate->tupdesc_change);
+ FreeTupleDesc(dstate->tupdesc);
+ tuplestore_end(dstate->tstore);
+
+ FreeDecodingContext(ctx);
+
+ ReplicationSlotRelease();
+ ReplicationSlotDrop(NameStr(dstate->slotname), false);
+ pfree(dstate);
+}
+
+/*
+ * The final steps of rebuild_relation() for concurrent processing.
+ *
+ * On entry, NewHeap is locked in AccessExclusiveLock mode. OldHeap and its
+ * clustering index (if one is passed) are still locked in a mode that allows
+ * concurrent data changes. On exit, both tables and their indexes are closed,
+ * but locked in AccessExclusiveLock mode.
+ */
+static void
+rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
+ Relation cl_index,
+ LogicalDecodingContext *decoding_ctx,
+ TransactionId frozenXid,
+ MultiXactId cutoffMulti)
+{
+ LOCKMODE lockmode_old PG_USED_FOR_ASSERTS_ONLY;
+ List *ind_oids_new;
+ Oid old_table_oid = RelationGetRelid(OldHeap);
+ Oid new_table_oid = RelationGetRelid(NewHeap);
+ List *ind_oids_old = RelationGetIndexList(OldHeap);
+ ListCell *lc,
+ *lc2;
+ char relpersistence;
+ bool is_system_catalog;
+ Oid ident_idx_old,
+ ident_idx_new;
+ XLogRecPtr wal_insert_ptr,
+ end_of_wal;
+ char dummy_rec_data = '\0';
+ Relation *ind_refs,
+ *ind_refs_p;
+ int nind;
+ ChangeDest chgdst;
+
+ /* Like in cluster_rel(). */
+ lockmode_old = ShareUpdateExclusiveLock;
+ Assert(CheckRelationLockedByMe(OldHeap, lockmode_old, false));
+ Assert(cl_index == NULL ||
+ CheckRelationLockedByMe(cl_index, lockmode_old, false));
+ /* This is expected from the caller. */
+ Assert(CheckRelationLockedByMe(NewHeap, AccessExclusiveLock, false));
+
+ ident_idx_old = RelationGetReplicaIndex(OldHeap);
+
+ /*
+ * Unlike the exclusive case, we build new indexes for the new relation
+ * rather than swapping the storage and reindexing the old relation. The
+ * point is that the index build can take some time, so we do it before we
+ * get AccessExclusiveLock on the old heap and therefore we cannot swap
+ * the heap storage yet.
+ *
+ * index_create() will lock the new indexes using AccessExclusiveLock - no
+ * need to change that. At the same time, we use ShareUpdateExclusiveLock
+ * to lock the existing indexes - that should be enough to prevent others
+ * from changing them while we're repacking the relation. The lock on
+ * table should prevent others from changing the index column list, but
+ * might not be enough for commands like ALTER INDEX ... SET ... (Those
+ * are not necessarily dangerous, but can make user confused if the
+ * changes they do get lost due to REPACK.)
+ */
+ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
+
+ /*
+ * Processing shouldn't start w/o valid identity index.
+ */
+ Assert(OidIsValid(ident_idx_old));
+
+ /* Find "identity index" on the new relation. */
+ ident_idx_new = InvalidOid;
+ forboth(lc, ind_oids_old, lc2, ind_oids_new)
+ {
+ Oid ind_old = lfirst_oid(lc);
+ Oid ind_new = lfirst_oid(lc2);
+
+ if (ident_idx_old == ind_old)
+ {
+ ident_idx_new = ind_new;
+ break;
+ }
+ }
+ if (!OidIsValid(ident_idx_new))
+
+ /*
+ * Should not happen, given our lock on the old relation.
+ */
+ ereport(ERROR,
+ (errmsg("identity index missing on the new relation")));
+
+ /* Gather information to apply concurrent changes. */
+ chgdst.rel = NewHeap;
+ chgdst.iistate = get_index_insert_state(NewHeap, ident_idx_new,
+ &chgdst.ident_index);
+ chgdst.ident_key = build_identity_key(ident_idx_new, OldHeap,
+ &chgdst.ident_key_nentries);
+
+ /*
+ * During testing, wait for another backend to perform concurrent data
+ * changes which we will process below.
+ */
+ INJECTION_POINT("repack-concurrently-before-lock", NULL);
+
+ /*
+ * Flush all WAL records inserted so far (possibly except for the last
+ * incomplete page, see GetInsertRecPtr), to minimize the amount of data
+ * we need to flush while holding exclusive lock on the source table.
+ */
+ wal_insert_ptr = GetInsertRecPtr();
+ XLogFlush(wal_insert_ptr);
+ end_of_wal = GetFlushRecPtr(NULL);
+
+ /*
+ * Apply concurrent changes first time, to minimize the time we need to
+ * hold AccessExclusiveLock. (Quite some amount of WAL could have been
+ * written during the data copying and index creation.)
+ */
+ process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+
+ /*
+ * Acquire AccessExclusiveLock on the table, its TOAST relation (if there
+ * is one), all its indexes, so that we can swap the files.
+ *
+ * Before that, unlock the index temporarily to avoid deadlock in case
+ * another transaction is trying to lock it while holding the lock on the
+ * table.
+ */
+ if (cl_index)
+ {
+ index_close(cl_index, ShareUpdateExclusiveLock);
+ cl_index = NULL;
+ }
+ /* For the same reason, unlock TOAST relation. */
+ if (OldHeap->rd_rel->reltoastrelid)
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+ /* Finally lock the table */
+ LockRelationOid(old_table_oid, AccessExclusiveLock);
+
+ /*
+ * Lock all indexes now, not only the clustering one: all indexes need to
+ * have their files swapped. While doing that, store their relation
+ * references in an array, to handle predicate locks below.
+ */
+ ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
+ nind = 0;
+ foreach(lc, ind_oids_old)
+ {
+ Oid ind_oid;
+ Relation index;
+
+ ind_oid = lfirst_oid(lc);
+ index = index_open(ind_oid, AccessExclusiveLock);
+
+ /*
+ * TODO 1) Do we need to check if ALTER INDEX was executed since the
+ * new index was created in build_new_indexes()? 2) Specifically for
+ * the clustering index, should check_index_is_clusterable() be called
+ * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
+ * table probably blocks all commands that affect the result of
+ * check_index_is_clusterable().)
+ */
+ *ind_refs_p = index;
+ ind_refs_p++;
+ nind++;
+ }
+
+ /*
+ * In addition, lock the OldHeap's TOAST relation exclusively - again, the
+ * lock is needed to swap the files.
+ */
+ if (OidIsValid(OldHeap->rd_rel->reltoastrelid))
+ LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
+
+ /*
+ * Tuples and pages of the old heap will be gone, but the heap will stay.
+ */
+ TransferPredicateLocksToHeapRelation(OldHeap);
+ /* The same for indexes. */
+ for (int i = 0; i < nind; i++)
+ {
+ Relation index = ind_refs[i];
+
+ TransferPredicateLocksToHeapRelation(index);
+
+ /*
+ * References to indexes on the old relation are not needed anymore,
+ * however locks stay till the end of the transaction.
+ */
+ index_close(index, NoLock);
+ }
+ pfree(ind_refs);
+
+ /*
+ * Flush anything we see in WAL, to make sure that all changes committed
+ * while we were waiting for the exclusive lock are available for
+ * decoding. This should not be necessary if all backends had
+ * synchronous_commit set, but we can't rely on this setting.
+ *
+ * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
+ * position, and GetLastImportantRecPtr() points at the start of the last
+ * record rather than at the end. Thus the simplest way to determine the
+ * insert position is to insert a dummy record and use its LSN.
+ *
+ * XXX Consider using GetLastImportantRecPtr() and adding the size of the
+ * last record (plus the total size of all the page headers the record
+ * spans)?
+ */
+ XLogBeginInsert();
+ XLogRegisterData(&dummy_rec_data, 1);
+ wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
+ XLogFlush(wal_insert_ptr);
+ end_of_wal = GetFlushRecPtr(NULL);
+
+ /* Apply the concurrent changes again. */
+ process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+
+ /* Remember info about rel before closing OldHeap */
+ relpersistence = OldHeap->rd_rel->relpersistence;
+ is_system_catalog = IsSystemRelation(OldHeap);
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_SWAP_REL_FILES);
+
+ /*
+ * Even ShareUpdateExclusiveLock should have prevented others from
+ * creating / dropping indexes (even using the CONCURRENTLY option), so we
+ * do not need to check whether the lists match.
+ */
+ forboth(lc, ind_oids_old, lc2, ind_oids_new)
+ {
+ Oid ind_old = lfirst_oid(lc);
+ Oid ind_new = lfirst_oid(lc2);
+ Oid mapped_tables[4];
+
+ /* Zero out possible results from swapped_relation_files */
+ memset(mapped_tables, 0, sizeof(mapped_tables));
+
+ swap_relation_files(ind_old, ind_new,
+ (old_table_oid == RelationRelationId),
+ false, /* swap_toast_by_content */
+ true,
+ InvalidTransactionId,
+ InvalidMultiXactId,
+ mapped_tables);
+
+#ifdef USE_ASSERT_CHECKING
+
+ /*
+ * Concurrent processing is not supported for system relations, so
+ * there should be no mapped tables.
+ */
+ for (int i = 0; i < 4; i++)
+ Assert(mapped_tables[i] == 0);
+#endif
+ }
+
+ /* The new indexes must be visible for deletion. */
+ CommandCounterIncrement();
+
+ /* Close the old heap but keep lock until transaction commit. */
+ table_close(OldHeap, NoLock);
+ /* Close the new heap. (We didn't have to open its indexes). */
+ table_close(NewHeap, NoLock);
+
+ /* Cleanup what we don't need anymore. (And close the identity index.) */
+ pfree(chgdst.ident_key);
+ free_index_insert_state(chgdst.iistate);
+
+ /*
+ * Swap the relations and their TOAST relations and TOAST indexes. This
+ * also drops the new relation and its indexes.
+ *
+ * (System catalogs are currently not supported.)
+ */
+ Assert(!is_system_catalog);
+ finish_heap_swap(old_table_oid, new_table_oid,
+ is_system_catalog,
+ false, /* swap_toast_by_content */
+ false, true, false,
+ frozenXid, cutoffMulti,
+ relpersistence);
+}
+
+/*
+ * Build indexes on NewHeap according to those on OldHeap.
+ *
+ * OldIndexes is the list of index OIDs on OldHeap. The contained indexes end
+ * up locked using ShareUpdateExclusiveLock.
+ *
+ * A list of OIDs of the corresponding indexes created on NewHeap is
+ * returned. The order of items does match, so we can use these arrays to swap
+ * index storage.
+ */
+static List *
+build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
+{
+ ListCell *lc;
+ List *result = NIL;
+
+ pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
+ PROGRESS_REPACK_PHASE_REBUILD_INDEX);
+
+ foreach(lc, OldIndexes)
+ {
+ Oid ind_oid,
+ ind_oid_new;
+ char *newName;
+ Relation ind;
+
+ ind_oid = lfirst_oid(lc);
+ ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+
+ newName = ChooseRelationName(get_rel_name(ind_oid),
+ NULL,
+ "repacknew",
+ get_rel_namespace(ind->rd_index->indrelid),
+ false);
+ ind_oid_new = index_create_copy(NewHeap, ind_oid,
+ ind->rd_rel->reltablespace, newName,
+ false);
+ result = lappend_oid(result, ind_oid_new);
+
+ index_close(ind, NoLock);
+ }
+
+ return result;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index a1fd4cab35b..85d289ca22b 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -892,7 +892,7 @@ refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
static void
refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersistence)
{
- finish_heap_swap(matviewOid, OIDNewHeap, false, false, true, true,
+ finish_heap_swap(matviewOid, OIDNewHeap, false, false, true, true, true,
RecentXmin, ReadNextMultiXactId(), relpersistence);
}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 1c9ef53be20..d3235df6c11 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -5992,6 +5992,7 @@ ATRewriteTables(AlterTableStmt *parsetree, List **wqueue, LOCKMODE lockmode,
finish_heap_swap(tab->relid, OIDNewHeap,
false, false, true,
!OidIsValid(tab->newTableSpace),
+ true,
RecentXmin,
ReadNextMultiXactId(),
persistence);
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index 6afa203983f..ae8b5d4066f 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -126,7 +126,7 @@ static void vac_truncate_clog(TransactionId frozenXID,
TransactionId lastSaneFrozenXid,
MultiXactId lastSaneMinMulti);
static bool vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
- BufferAccessStrategy bstrategy);
+ BufferAccessStrategy bstrategy, bool isTopLevel);
static double compute_parallel_delay(void);
static VacOptValue get_vacoptval_from_boolean(DefElem *def);
static bool vac_tid_reaped(ItemPointer itemptr, void *state);
@@ -629,7 +629,8 @@ vacuum(List *relations, const VacuumParams params, BufferAccessStrategy bstrateg
if (params.options & VACOPT_VACUUM)
{
- if (!vacuum_rel(vrel->oid, vrel->relation, params, bstrategy))
+ if (!vacuum_rel(vrel->oid, vrel->relation, params, bstrategy,
+ isTopLevel))
continue;
}
@@ -1999,7 +2000,7 @@ vac_truncate_clog(TransactionId frozenXID,
*/
static bool
vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
- BufferAccessStrategy bstrategy)
+ BufferAccessStrategy bstrategy, bool isTopLevel)
{
LOCKMODE lmode;
Relation rel;
@@ -2290,7 +2291,7 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
/* VACUUM FULL is a variant of REPACK; see cluster.c */
cluster_rel(REPACK_COMMAND_VACUUMFULL, rel, InvalidOid,
- &cluster_params);
+ &cluster_params, isTopLevel);
/* cluster_rel closes the relation, but keeps lock */
rel = NULL;
@@ -2333,7 +2334,8 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params,
toast_vacuum_params.options |= VACOPT_PROCESS_MAIN;
toast_vacuum_params.toast_parent = relid;
- vacuum_rel(toast_relid, NULL, toast_vacuum_params, bstrategy);
+ vacuum_rel(toast_relid, NULL, toast_vacuum_params, bstrategy,
+ isTopLevel);
}
/*
diff --git a/src/backend/meson.build b/src/backend/meson.build
index b831a541652..5c148131217 100644
--- a/src/backend/meson.build
+++ b/src/backend/meson.build
@@ -194,5 +194,6 @@ pg_test_mod_args = pg_mod_args + {
subdir('jit/llvm')
subdir('replication/libpqwalreceiver')
subdir('replication/pgoutput')
+subdir('replication/pgoutput_repack')
subdir('snowball')
subdir('utils/mb/conversion_procs')
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index cc03f0706e9..a956892f42f 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -33,6 +33,7 @@
#include "access/xlogreader.h"
#include "access/xlogrecord.h"
#include "catalog/pg_control.h"
+#include "commands/cluster.h"
#include "replication/decode.h"
#include "replication/logical.h"
#include "replication/message.h"
@@ -472,6 +473,88 @@ heap_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
TransactionId xid = XLogRecGetXid(buf->record);
SnapBuild *builder = ctx->snapshot_builder;
+ /*
+ * If the change is not intended for logical decoding, do not even
+ * establish transaction for it - REPACK CONCURRENTLY is the typical use
+ * case.
+ *
+ * First, check if REPACK CONCURRENTLY is being performed by this backend.
+ * If so, only decode data changes of the table that it is processing, and
+ * the changes of its TOAST relation.
+ *
+ * (TOAST locator should not be set unless the main is.)
+ */
+ Assert(!OidIsValid(repacked_rel_toast_locator.relNumber) ||
+ OidIsValid(repacked_rel_locator.relNumber));
+
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ {
+ XLogReaderState *r = buf->record;
+ RelFileLocator locator;
+
+ /* Not all records contain the block. */
+ if (XLogRecGetBlockTagExtended(r, 0, &locator, NULL, NULL, NULL) &&
+ !RelFileLocatorEquals(locator, repacked_rel_locator) &&
+ (!OidIsValid(repacked_rel_toast_locator.relNumber) ||
+ !RelFileLocatorEquals(locator, repacked_rel_toast_locator)))
+ return;
+ }
+
+ /*
+ * Second, skip records which do not contain sufficient information for
+ * the decoding.
+ *
+ * The problem we solve here is that REPACK CONCURRENTLY generates WAL
+ * when doing changes in the new table. Those changes should not be useful
+ * for any other user (such as logical replication subscription) because
+ * the new table will eventually be dropped (after REPACK CONCURRENTLY has
+ * assigned its file to the "old table").
+ */
+ switch (info)
+ {
+ case XLOG_HEAP_INSERT:
+ {
+ xl_heap_insert *rec;
+
+ rec = (xl_heap_insert *) XLogRecGetData(buf->record);
+
+ /*
+ * This does happen when 1) raw_heap_insert marks the TOAST
+ * record as HEAP_INSERT_NO_LOGICAL, 2) REPACK CONCURRENTLY
+ * replays inserts performed by other backends.
+ */
+ if ((rec->flags & XLH_INSERT_CONTAINS_NEW_TUPLE) == 0)
+ return;
+
+ break;
+ }
+
+ case XLOG_HEAP_HOT_UPDATE:
+ case XLOG_HEAP_UPDATE:
+ {
+ xl_heap_update *rec;
+
+ rec = (xl_heap_update *) XLogRecGetData(buf->record);
+ if ((rec->flags &
+ (XLH_UPDATE_CONTAINS_NEW_TUPLE |
+ XLH_UPDATE_CONTAINS_OLD_TUPLE |
+ XLH_UPDATE_CONTAINS_OLD_KEY)) == 0)
+ return;
+
+ break;
+ }
+
+ case XLOG_HEAP_DELETE:
+ {
+ xl_heap_delete *rec;
+
+ rec = (xl_heap_delete *) XLogRecGetData(buf->record);
+ if (rec->flags & XLH_DELETE_NO_LOGICAL)
+ return;
+ break;
+ }
+ }
+
ReorderBufferProcessXid(ctx->reorder, xid, buf->origptr);
/*
@@ -512,6 +595,17 @@ heap_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
break;
case XLOG_HEAP_TRUNCATE:
+ /* Is REPACK (CONCURRENTLY) being run by this backend? */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+
+ /*
+ * TRUNCATE changes rd_locator of the relation, so it'd break
+ * REPACK (CONCURRENTLY). In fact it should not happen because
+ * TRUNCATE needs AccessExclusiveLock on the table. Should we
+ * only use Assert() here?
+ */
+ ereport(ERROR,
+ (errmsg("TRUNCATE encountered while doing REPACK (CONCURRENTLY)")));
if (SnapBuildProcessChange(builder, xid, buf->origptr) &&
!ctx->fast_forward)
DecodeTruncate(ctx, buf);
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index a3730804428..7643dfe31bb 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -486,6 +486,27 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
return SnapBuildMVCCFromHistoric(snap, true);
}
+/*
+ * Build an MVCC snapshot for the initial data load performed by REPACK
+ * CONCURRENTLY command.
+ *
+ * The snapshot will only be used to scan one particular relation, which is
+ * treated like a catalog (therefore ->building_full_snapshot is not
+ * important), and the caller should already have a replication slot setup (so
+ * we do not set MyProc->xmin). XXX Do we yet need to add some restrictions?
+ */
+Snapshot
+SnapBuildInitialSnapshotForRepack(SnapBuild *builder)
+{
+ Snapshot snap;
+
+ Assert(builder->state == SNAPBUILD_CONSISTENT);
+ Assert(builder->building_full_snapshot);
+
+ snap = SnapBuildBuildSnapshot(builder);
+ return SnapBuildMVCCFromHistoric(snap, false);
+}
+
/*
* Turn a historic MVCC snapshot into an ordinary MVCC snapshot.
*
diff --git a/src/backend/replication/pgoutput_repack/Makefile b/src/backend/replication/pgoutput_repack/Makefile
new file mode 100644
index 00000000000..4efeb713b70
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/Makefile
@@ -0,0 +1,32 @@
+#-------------------------------------------------------------------------
+#
+# Makefile--
+# Makefile for src/backend/replication/pgoutput_repack
+#
+# IDENTIFICATION
+# src/backend/replication/pgoutput_repack
+#
+#-------------------------------------------------------------------------
+
+subdir = src/backend/replication/pgoutput_repack
+top_builddir = ../../../..
+include $(top_builddir)/src/Makefile.global
+
+OBJS = \
+ $(WIN32RES) \
+ pgoutput_repack.o
+PGFILEDESC = "pgoutput_repack - logical replication output plugin for REPACK command"
+NAME = pgoutput_repack
+
+all: all-shared-lib
+
+include $(top_srcdir)/src/Makefile.shlib
+
+install: all installdirs install-lib
+
+installdirs: installdirs-lib
+
+uninstall: uninstall-lib
+
+clean distclean: clean-lib
+ rm -f $(OBJS)
diff --git a/src/backend/replication/pgoutput_repack/meson.build b/src/backend/replication/pgoutput_repack/meson.build
new file mode 100644
index 00000000000..133e865a4a0
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/meson.build
@@ -0,0 +1,18 @@
+# Copyright (c) 2022-2024, PostgreSQL Global Development Group
+
+pgoutput_repack_sources = files(
+ 'pgoutput_repack.c',
+)
+
+if host_system == 'windows'
+ pgoutput_repack_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+ '--NAME', 'pgoutput_repack',
+ '--FILEDESC', 'pgoutput_repack - logical replication output plugin for REPACK command',])
+endif
+
+pgoutput_repack = shared_module('pgoutput_repack',
+ pgoutput_repack_sources,
+ kwargs: pg_mod_args,
+)
+
+backend_targets += pgoutput_repack
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
new file mode 100644
index 00000000000..c8930640a0d
--- /dev/null
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -0,0 +1,240 @@
+/*-------------------------------------------------------------------------
+ *
+ * pgoutput_repack.c
+ * Logical Replication output plugin for REPACK command
+ *
+ * Copyright (c) 2012-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * src/backend/replication/pgoutput_repack/pgoutput_repack.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/heaptoast.h"
+#include "commands/cluster.h"
+#include "replication/snapbuild.h"
+#include "utils/memutils.h"
+
+PG_MODULE_MAGIC;
+
+static void plugin_startup(LogicalDecodingContext *ctx,
+ OutputPluginOptions *opt, bool is_init);
+static void plugin_shutdown(LogicalDecodingContext *ctx);
+static void plugin_begin_txn(LogicalDecodingContext *ctx,
+ ReorderBufferTXN *txn);
+static void plugin_commit_txn(LogicalDecodingContext *ctx,
+ ReorderBufferTXN *txn, XLogRecPtr commit_lsn);
+static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ Relation rel, ReorderBufferChange *change);
+static void store_change(LogicalDecodingContext *ctx,
+ ConcurrentChangeKind kind, HeapTuple tuple);
+
+void
+_PG_output_plugin_init(OutputPluginCallbacks *cb)
+{
+ AssertVariableIsOfType(&_PG_output_plugin_init, LogicalOutputPluginInit);
+
+ cb->startup_cb = plugin_startup;
+ cb->begin_cb = plugin_begin_txn;
+ cb->change_cb = plugin_change;
+ cb->commit_cb = plugin_commit_txn;
+ cb->shutdown_cb = plugin_shutdown;
+}
+
+
+/* initialize this plugin */
+static void
+plugin_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt,
+ bool is_init)
+{
+ ctx->output_plugin_private = NULL;
+
+ /* Probably unnecessary, as we don't use the SQL interface ... */
+ opt->output_type = OUTPUT_PLUGIN_BINARY_OUTPUT;
+
+ if (ctx->output_plugin_options != NIL)
+ {
+ ereport(ERROR,
+ (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("This plugin does not expect any options")));
+ }
+}
+
+static void
+plugin_shutdown(LogicalDecodingContext *ctx)
+{
+}
+
+/*
+ * As we don't release the slot during processing of particular table, there's
+ * no room for SQL interface, even for debugging purposes. Therefore we need
+ * neither OutputPluginPrepareWrite() nor OutputPluginWrite() in the plugin
+ * callbacks. (Although we might want to write custom callbacks, this API
+ * seems to be unnecessarily generic for our purposes.)
+ */
+
+/* BEGIN callback */
+static void
+plugin_begin_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn)
+{
+}
+
+/* COMMIT callback */
+static void
+plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ XLogRecPtr commit_lsn)
+{
+}
+
+/*
+ * Callback for individual changed tuples
+ */
+static void
+plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
+ Relation relation, ReorderBufferChange *change)
+{
+ RepackDecodingState *dstate;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ /* Only interested in one particular relation. */
+ if (relation->rd_id != dstate->relid)
+ return;
+
+ /* Decode entry depending on its type */
+ switch (change->action)
+ {
+ case REORDER_BUFFER_CHANGE_INSERT:
+ {
+ HeapTuple newtuple;
+
+ newtuple = change->data.tp.newtuple != NULL ?
+ change->data.tp.newtuple : NULL;
+
+ /*
+ * Identity checks in the main function should have made this
+ * impossible.
+ */
+ if (newtuple == NULL)
+ elog(ERROR, "Incomplete insert info.");
+
+ store_change(ctx, CHANGE_INSERT, newtuple);
+ }
+ break;
+ case REORDER_BUFFER_CHANGE_UPDATE:
+ {
+ HeapTuple oldtuple,
+ newtuple;
+
+ oldtuple = change->data.tp.oldtuple != NULL ?
+ change->data.tp.oldtuple : NULL;
+ newtuple = change->data.tp.newtuple != NULL ?
+ change->data.tp.newtuple : NULL;
+
+ if (newtuple == NULL)
+ elog(ERROR, "Incomplete update info.");
+
+ if (oldtuple != NULL)
+ store_change(ctx, CHANGE_UPDATE_OLD, oldtuple);
+
+ store_change(ctx, CHANGE_UPDATE_NEW, newtuple);
+ }
+ break;
+ case REORDER_BUFFER_CHANGE_DELETE:
+ {
+ HeapTuple oldtuple;
+
+ oldtuple = change->data.tp.oldtuple ?
+ change->data.tp.oldtuple : NULL;
+
+ if (oldtuple == NULL)
+ elog(ERROR, "Incomplete delete info.");
+
+ store_change(ctx, CHANGE_DELETE, oldtuple);
+ }
+ break;
+ default:
+ /* Should not come here */
+ Assert(false);
+ break;
+ }
+}
+
+/* Store concurrent data change. */
+static void
+store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
+ HeapTuple tuple)
+{
+ RepackDecodingState *dstate;
+ char *change_raw;
+ ConcurrentChange change;
+ bool flattened = false;
+ Size size;
+ Datum values[1];
+ bool isnull[1];
+ char *dst;
+
+ dstate = (RepackDecodingState *) ctx->output_writer_private;
+
+ size = VARHDRSZ + SizeOfConcurrentChange;
+
+ /*
+ * ReorderBufferCommit() stores the TOAST chunks in its private memory
+ * context and frees them after having called apply_change(). Therefore
+ * we need flat copy (including TOAST) that we eventually copy into the
+ * memory context which is available to decode_concurrent_changes().
+ */
+ if (HeapTupleHasExternal(tuple))
+ {
+ /*
+ * toast_flatten_tuple_to_datum() might be more convenient but we
+ * don't want the decompression it does.
+ */
+ tuple = toast_flatten_tuple(tuple, dstate->tupdesc);
+ flattened = true;
+ }
+
+ size += tuple->t_len;
+ if (size >= MaxAllocSize)
+ elog(ERROR, "Change is too big.");
+
+ /* Construct the change. */
+ change_raw = (char *) palloc0(size);
+ SET_VARSIZE(change_raw, size);
+
+ /*
+ * Since the varlena alignment might not be sufficient for the structure,
+ * set the fields in a local instance and remember where it should
+ * eventually be copied.
+ */
+ change.kind = kind;
+ dst = (char *) VARDATA(change_raw);
+
+ /*
+ * Copy the tuple.
+ *
+ * Note: change->tup_data.t_data must be fixed on retrieval!
+ */
+ memcpy(&change.tup_data, tuple, sizeof(HeapTupleData));
+ memcpy(dst, &change, SizeOfConcurrentChange);
+ dst += SizeOfConcurrentChange;
+ memcpy(dst, tuple->t_data, tuple->t_len);
+
+ /* The data has been copied. */
+ if (flattened)
+ pfree(tuple);
+
+ /* Store as tuple of 1 bytea column. */
+ values[0] = PointerGetDatum(change_raw);
+ isnull[0] = false;
+ tuplestore_putvalues(dstate->tstore, dstate->tupdesc_change,
+ values, isnull);
+
+ /* Accounting. */
+ dstate->nchanges++;
+
+ /* Cleanup. */
+ pfree(change_raw);
+}
diff --git a/src/backend/storage/lmgr/generate-lwlocknames.pl b/src/backend/storage/lmgr/generate-lwlocknames.pl
index cd3e43c448a..519f3953638 100644
--- a/src/backend/storage/lmgr/generate-lwlocknames.pl
+++ b/src/backend/storage/lmgr/generate-lwlocknames.pl
@@ -162,7 +162,7 @@ while (<$lwlocklist>)
die
"$wait_event_lwlocks[$lwlock_count] defined in wait_event_names.txt but "
- . " missing from lwlocklist.h"
+ . "missing from lwlocklist.h"
if $lwlock_count < scalar @wait_event_lwlocks;
die
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index 4cf32ffe833..93fc3037110 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -214,7 +214,6 @@ static List *exportedSnapshots = NIL;
/* Prototypes for local functions */
static void UnregisterSnapshotNoOwner(Snapshot snapshot);
-static void FreeSnapshot(Snapshot snapshot);
static void SnapshotResetXmin(void);
/* ResourceOwner callbacks to track snapshot references */
@@ -659,7 +658,7 @@ CopySnapshot(Snapshot snapshot)
* FreeSnapshot
* Free the memory associated with a snapshot.
*/
-static void
+void
FreeSnapshot(Snapshot snapshot)
{
Assert(snapshot->regd_count == 0);
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 626d9f1c98b..0fcf343d3af 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -5075,8 +5075,8 @@ match_previous_words(int pattern_id,
* one word, so the above test is correct.
*/
if (ends_with(prev_wd, '(') || ends_with(prev_wd, ','))
- COMPLETE_WITH("ANALYZE", "VERBOSE");
- else if (TailMatches("ANALYZE", "VERBOSE"))
+ COMPLETE_WITH("ANALYZE", "CONCURRENTLY", "VERBOSE");
+ else if (TailMatches("ANALYZE", "CONCURRENTLY", "VERBOSE"))
COMPLETE_WITH("ON", "OFF");
}
diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 632c4332a8c..b7cd25896f6 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -361,14 +361,15 @@ extern void heap_multi_insert(Relation relation, TupleTableSlot **slots,
BulkInsertState bistate);
extern TM_Result heap_delete(Relation relation, const ItemPointerData *tid,
CommandId cid, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart);
+ TM_FailureData *tmfd, bool changingPart,
+ bool wal_logical);
extern void heap_finish_speculative(Relation relation, const ItemPointerData *tid);
extern void heap_abort_speculative(Relation relation, const ItemPointerData *tid);
extern TM_Result heap_update(Relation relation, const ItemPointerData *otid,
HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
TM_FailureData *tmfd, LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes);
+ TU_UpdateIndexes *update_indexes, bool wal_logical);
extern TM_Result heap_lock_tuple(Relation relation, HeapTuple tuple,
CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy,
bool follow_updates,
diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h
index 16c2b2e3c9c..2cc49fd48de 100644
--- a/src/include/access/heapam_xlog.h
+++ b/src/include/access/heapam_xlog.h
@@ -104,6 +104,8 @@
#define XLH_DELETE_CONTAINS_OLD_KEY (1<<2)
#define XLH_DELETE_IS_SUPER (1<<3)
#define XLH_DELETE_IS_PARTITION_MOVE (1<<4)
+/* See heap_delete() */
+#define XLH_DELETE_NO_LOGICAL (1<<5)
/* convenience macro for checking whether any form of old tuple was logged */
#define XLH_DELETE_CONTAINS_OLD \
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 2fa790b6bf5..d8f76d325f9 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -22,6 +22,7 @@
#include "access/xact.h"
#include "commands/vacuum.h"
#include "executor/tuptable.h"
+#include "replication/logical.h"
#include "storage/read_stream.h"
#include "utils/rel.h"
#include "utils/snapshot.h"
@@ -629,6 +630,8 @@ typedef struct TableAmRoutine
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1646,6 +1649,10 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator)
* not needed for the relation's AM
* - *xid_cutoff - ditto
* - *multi_cutoff - ditto
+ * - snapshot - if != NULL, ignore data changes done by transactions that this
+ * (MVCC) snapshot considers still in-progress or in the future.
+ * - decoding_ctx - logical decoding context, to capture concurrent data
+ * changes.
*
* Output parameters:
* - *xid_cutoff - rel's new relfrozenxid value, may be invalid
@@ -1658,6 +1665,8 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
+ Snapshot snapshot,
+ LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1666,6 +1675,7 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
{
OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex,
use_sort, OldestXmin,
+ snapshot, decoding_ctx,
xid_cutoff, multi_cutoff,
num_tuples, tups_vacuumed,
tups_recently_dead);
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 652542e8e65..b43a1740053 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -13,10 +13,15 @@
#ifndef CLUSTER_H
#define CLUSTER_H
+#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
+#include "replication/logical.h"
#include "storage/lock.h"
+#include "storage/relfilelocator.h"
#include "utils/relcache.h"
+#include "utils/resowner.h"
+#include "utils/tuplestore.h"
/* flag bits for ClusterParams->options */
@@ -25,6 +30,8 @@
#define CLUOPT_RECHECK_ISCLUSTERED 0x04 /* recheck relation state for
* indisclustered */
#define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */
+#define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */
+
/* options for CLUSTER */
typedef struct ClusterParams
@@ -33,14 +40,94 @@ typedef struct ClusterParams
} ClusterParams;
+/*
+ * The following definitions are used by REPACK CONCURRENTLY.
+ */
+
+extern RelFileLocator repacked_rel_locator;
+extern RelFileLocator repacked_rel_toast_locator;
+
+typedef enum
+{
+ CHANGE_INSERT,
+ CHANGE_UPDATE_OLD,
+ CHANGE_UPDATE_NEW,
+ CHANGE_DELETE
+} ConcurrentChangeKind;
+
+typedef struct ConcurrentChange
+{
+ /* See the enum above. */
+ ConcurrentChangeKind kind;
+
+ /*
+ * The actual tuple.
+ *
+ * The tuple data follows the ConcurrentChange structure. Before use make
+ * sure the tuple is correctly aligned (ConcurrentChange can be stored as
+ * bytea) and that tuple->t_data is fixed.
+ */
+ HeapTupleData tup_data;
+} ConcurrentChange;
+
+#define SizeOfConcurrentChange (offsetof(ConcurrentChange, tup_data) + \
+ sizeof(HeapTupleData))
+
+/*
+ * Logical decoding state.
+ *
+ * Here we store the data changes that we decode from WAL while the table
+ * contents is being copied to a new storage. Also the necessary metadata
+ * needed to apply these changes to the table is stored here.
+ */
+typedef struct RepackDecodingState
+{
+ /* The relation whose changes we're decoding. */
+ Oid relid;
+
+ /* Replication slot name. */
+ NameData slotname;
+
+ /*
+ * Decoded changes are stored here. Although we try to avoid excessive
+ * batches, it can happen that the changes need to be stored to disk. The
+ * tuplestore does this transparently.
+ */
+ Tuplestorestate *tstore;
+
+ /* The current number of changes in tstore. */
+ double nchanges;
+
+ /*
+ * Descriptor to store the ConcurrentChange structure serialized (bytea).
+ * We can't store the tuple directly because tuplestore only supports
+ * minimum tuple and we may need to transfer OID system column from the
+ * output plugin. Also we need to transfer the change kind, so it's better
+ * to put everything in the structure than to use 2 tuplestores "in
+ * parallel".
+ */
+ TupleDesc tupdesc_change;
+
+ /* Tuple descriptor needed to update indexes. */
+ TupleDesc tupdesc;
+
+ /* Slot to retrieve data from tstore. */
+ TupleTableSlot *tsslot;
+
+ ResourceOwner resowner;
+} RepackDecodingState;
+
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid indexOid,
- ClusterParams *params);
+ ClusterParams *params, bool isTopLevel);
extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid,
LOCKMODE lockmode);
extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_internal);
+extern void repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
+ XLogRecPtr end_of_wal);
+
extern Oid make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
char relpersistence, LOCKMODE lockmode);
extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
@@ -48,6 +135,7 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
bool swap_toast_by_content,
bool check_constraints,
bool is_internal,
+ bool reindex,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence);
diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h
index 8d68bcbef95..18cb482ac26 100644
--- a/src/include/commands/progress.h
+++ b/src/include/commands/progress.h
@@ -86,10 +86,12 @@
#define PROGRESS_REPACK_PHASE 1
#define PROGRESS_REPACK_INDEX_RELID 2
#define PROGRESS_REPACK_HEAP_TUPLES_SCANNED 3
-#define PROGRESS_REPACK_HEAP_TUPLES_WRITTEN 4
-#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 5
-#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 6
-#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 7
+#define PROGRESS_REPACK_HEAP_TUPLES_INSERTED 4
+#define PROGRESS_REPACK_HEAP_TUPLES_UPDATED 5
+#define PROGRESS_REPACK_HEAP_TUPLES_DELETED 6
+#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 7
+#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 8
+#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 9
/*
* Phases of repack (as advertised via PROGRESS_REPACK_PHASE).
@@ -98,9 +100,10 @@
#define PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP 2
#define PROGRESS_REPACK_PHASE_SORT_TUPLES 3
#define PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP 4
-#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 5
-#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 6
-#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 7
+#define PROGRESS_REPACK_PHASE_CATCH_UP 5
+#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 6
+#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 7
+#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 8
/* Progress parameters for CREATE INDEX */
/* 3, 4 and 5 reserved for "waitfor" metrics */
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 6d4d2d1814c..802fc4b0823 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,6 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
extern void SnapBuildSnapDecRefcount(Snapshot snap);
extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
+extern Snapshot SnapBuildInitialSnapshotForRepack(SnapBuild *builder);
extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
extern void SnapBuildClearExportedSnapshot(void);
diff --git a/src/include/storage/lockdefs.h b/src/include/storage/lockdefs.h
index 7f3ba0352f6..2739327b0da 100644
--- a/src/include/storage/lockdefs.h
+++ b/src/include/storage/lockdefs.h
@@ -36,8 +36,8 @@ typedef int LOCKMODE;
#define AccessShareLock 1 /* SELECT */
#define RowShareLock 2 /* SELECT FOR UPDATE/FOR SHARE */
#define RowExclusiveLock 3 /* INSERT, UPDATE, DELETE */
-#define ShareUpdateExclusiveLock 4 /* VACUUM (non-FULL), ANALYZE, CREATE
- * INDEX CONCURRENTLY */
+#define ShareUpdateExclusiveLock 4 /* VACUUM (non-exclusive), ANALYZE, CREATE
+ * INDEX CONCURRENTLY, REPACK CONCURRENTLY */
#define ShareLock 5 /* CREATE INDEX (WITHOUT CONCURRENTLY) */
#define ShareRowExclusiveLock 6 /* like EXCLUSIVE MODE, but allows ROW
* SHARE */
diff --git a/src/include/utils/snapmgr.h b/src/include/utils/snapmgr.h
index f65f83c85cd..1f821fd2ccd 100644
--- a/src/include/utils/snapmgr.h
+++ b/src/include/utils/snapmgr.h
@@ -64,6 +64,8 @@ extern Snapshot GetLatestSnapshot(void);
extern void SnapshotSetCommandId(CommandId curcid);
extern Snapshot CopySnapshot(Snapshot snapshot);
+extern void FreeSnapshot(Snapshot snapshot);
+
extern Snapshot GetCatalogSnapshot(Oid relid);
extern Snapshot GetNonHistoricCatalogSnapshot(Oid relid);
extern void InvalidateCatalogSnapshot(void);
diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile
index c85034eb8cc..a9769f1d99f 100644
--- a/src/test/modules/injection_points/Makefile
+++ b/src/test/modules/injection_points/Makefile
@@ -14,12 +14,15 @@ REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress
ISOLATION = basic \
inplace \
+ repack \
+ repack_toast \
syscache-update-pruned \
index-concurrently-upsert \
index-concurrently-upsert-predicate \
reindex-concurrently-upsert \
reindex-concurrently-upsert-on-constraint \
reindex-concurrently-upsert-partitioned
+ISOLATION_OPTS = --temp-config $(top_srcdir)/src/test/modules/injection_points/logical.conf
# The injection points are cluster-wide, so disable installcheck
NO_INSTALLCHECK = 1
diff --git a/src/test/modules/injection_points/expected/repack.out b/src/test/modules/injection_points/expected/repack.out
new file mode 100644
index 00000000000..b575e9052ee
--- /dev/null
+++ b/src/test/modules/injection_points/expected/repack.out
@@ -0,0 +1,113 @@
+Parsed test spec with 2 sessions
+
+starting permutation: wait_before_lock change_existing change_new change_subxact1 change_subxact2 check2 wakeup_before_lock check1
+injection_points_attach
+-----------------------
+
+(1 row)
+
+step wait_before_lock:
+ REPACK (CONCURRENTLY) repack_test USING INDEX repack_test_pkey;
+ <waiting ...>
+step change_existing:
+ UPDATE repack_test SET i=10 where i=1;
+ UPDATE repack_test SET j=20 where i=2;
+ UPDATE repack_test SET i=30 where i=3;
+ UPDATE repack_test SET i=40 where i=30;
+ DELETE FROM repack_test WHERE i=4;
+
+step change_new:
+ INSERT INTO repack_test(i, j) VALUES (5, 5), (6, 6), (7, 7), (8, 8);
+ UPDATE repack_test SET i=50 where i=5;
+ UPDATE repack_test SET j=60 where i=6;
+ DELETE FROM repack_test WHERE i=7;
+
+step change_subxact1:
+ BEGIN;
+ INSERT INTO repack_test(i, j) VALUES (100, 100);
+ SAVEPOINT s1;
+ UPDATE repack_test SET i=101 where i=100;
+ SAVEPOINT s2;
+ UPDATE repack_test SET i=102 where i=101;
+ COMMIT;
+
+step change_subxact2:
+ BEGIN;
+ SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 110);
+ ROLLBACK TO SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 111);
+ COMMIT;
+
+step check2:
+ INSERT INTO relfilenodes(node)
+ SELECT relfilenode FROM pg_class WHERE relname='repack_test';
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+
+ i| j
+---+---
+ 2| 20
+ 6| 60
+ 8| 8
+ 10| 1
+ 40| 3
+ 50| 5
+102|100
+110|111
+(8 rows)
+
+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_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ SELECT count(*)
+ FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j)
+ WHERE d1.i ISNULL OR d2.i ISNULL;
+
+count
+-----
+ 2
+(1 row)
+
+ i| j
+---+---
+ 2| 20
+ 6| 60
+ 8| 8
+ 10| 1
+ 40| 3
+ 50| 5
+102|100
+110|111
+(8 rows)
+
+count
+-----
+ 0
+(1 row)
+
+injection_points_detach
+-----------------------
+
+(1 row)
+
diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out
new file mode 100644
index 00000000000..4f866a74e32
--- /dev/null
+++ b/src/test/modules/injection_points/expected/repack_toast.out
@@ -0,0 +1,64 @@
+Parsed test spec with 2 sessions
+
+starting permutation: wait_before_lock change check2 wakeup_before_lock check1
+injection_points_attach
+-----------------------
+
+(1 row)
+
+step wait_before_lock:
+ REPACK (CONCURRENTLY) repack_test;
+ <waiting ...>
+step change:
+ UPDATE repack_test SET j=get_long_string() where i=2;
+ DELETE FROM repack_test WHERE i=3;
+ INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+
+step check2:
+ INSERT INTO relfilenodes(node)
+ SELECT c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+
+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 c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ SELECT count(*)
+ FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j)
+ WHERE d1.i ISNULL OR d2.i ISNULL;
+
+count
+-----
+ 4
+(1 row)
+
+count
+-----
+ 0
+(1 row)
+
+injection_points_detach
+-----------------------
+
+(1 row)
+
diff --git a/src/test/modules/injection_points/logical.conf b/src/test/modules/injection_points/logical.conf
new file mode 100644
index 00000000000..e3d257315fa
--- /dev/null
+++ b/src/test/modules/injection_points/logical.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build
index 8d6f662040d..b72bfb8ff06 100644
--- a/src/test/modules/injection_points/meson.build
+++ b/src/test/modules/injection_points/meson.build
@@ -45,6 +45,8 @@ tests += {
'specs': [
'basic',
'inplace',
+ 'repack',
+ 'repack_toast',
'syscache-update-pruned',
'index-concurrently-upsert',
'index-concurrently-upsert-predicate',
@@ -55,5 +57,7 @@ tests += {
'runningcheck': false, # see syscache-update-pruned
# Some tests wait for all snapshots, so avoid parallel execution
'runningcheck-parallel': false,
+ # 'repack' requires wal_level = 'logical'.
+ 'regress_args': ['--temp-config', files('logical.conf')],
},
}
diff --git a/src/test/modules/injection_points/specs/repack.spec b/src/test/modules/injection_points/specs/repack.spec
new file mode 100644
index 00000000000..d727a9b056b
--- /dev/null
+++ b/src/test/modules/injection_points/specs/repack.spec
@@ -0,0 +1,142 @@
+# REPACK (CONCURRENTLY) ... USING INDEX ...;
+setup
+{
+ CREATE EXTENSION injection_points;
+
+ CREATE TABLE repack_test(i int PRIMARY KEY, j int);
+ INSERT INTO repack_test(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_test;
+ 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_test USING INDEX repack_test_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_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ 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 change_existing
+{
+ UPDATE repack_test SET i=10 where i=1;
+ UPDATE repack_test SET j=20 where i=2;
+ UPDATE repack_test SET i=30 where i=3;
+ UPDATE repack_test SET i=40 where i=30;
+ DELETE FROM repack_test WHERE i=4;
+}
+# Insert new rows and UPDATE / DELETE some of them. Again, update both key and
+# non-key column.
+step change_new
+{
+ INSERT INTO repack_test(i, j) VALUES (5, 5), (6, 6), (7, 7), (8, 8);
+ UPDATE repack_test SET i=50 where i=5;
+ UPDATE repack_test SET j=60 where i=6;
+ DELETE FROM repack_test WHERE i=7;
+}
+
+# When applying concurrent data changes, we should see the effects of an
+# in-progress subtransaction.
+#
+# XXX Not sure this test is useful now - it was designed for the patch that
+# preserves tuple visibility and which therefore modifies
+# TransactionIdIsCurrentTransactionId().
+step change_subxact1
+{
+ BEGIN;
+ INSERT INTO repack_test(i, j) VALUES (100, 100);
+ SAVEPOINT s1;
+ UPDATE repack_test SET i=101 where i=100;
+ SAVEPOINT s2;
+ UPDATE repack_test SET i=102 where i=101;
+ COMMIT;
+}
+
+# When applying concurrent data changes, we should not see the effects of a
+# rolled back subtransaction.
+#
+# XXX Is this test useful? See above.
+step change_subxact2
+{
+ BEGIN;
+ SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 110);
+ ROLLBACK TO SAVEPOINT s1;
+ INSERT INTO repack_test(i, j) VALUES (110, 111);
+ COMMIT;
+}
+
+# Check the table from the perspective of s2.
+step check2
+{
+ INSERT INTO relfilenodes(node)
+ SELECT relfilenode FROM pg_class WHERE relname='repack_test';
+
+ SELECT i, j FROM repack_test ORDER BY i, j;
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+}
+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
+ change_existing
+ change_new
+ change_subxact1
+ change_subxact2
+ check2
+ wakeup_before_lock
+ check1
diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec
new file mode 100644
index 00000000000..b48abf21450
--- /dev/null
+++ b/src/test/modules/injection_points/specs/repack_toast.spec
@@ -0,0 +1,105 @@
+# REPACK (CONCURRENTLY);
+#
+# Test handling of TOAST. At the same time, no tuplesort.
+setup
+{
+ CREATE EXTENSION injection_points;
+
+ -- Return a string that needs to be TOASTed.
+ CREATE FUNCTION get_long_string()
+ RETURNS text
+ LANGUAGE sql as $$
+ SELECT string_agg(chr(65 + trunc(25 * random())::int), '')
+ FROM generate_series(1, 2048) s(x);
+ $$;
+
+ CREATE TABLE repack_test(i int PRIMARY KEY, j text);
+ INSERT INTO repack_test(i, j) VALUES (1, get_long_string()),
+ (2, get_long_string()), (3, get_long_string());
+
+ CREATE TABLE relfilenodes(node oid);
+
+ CREATE TABLE data_s1(i int, j text);
+ CREATE TABLE data_s2(i int, j text);
+}
+
+teardown
+{
+ DROP TABLE repack_test;
+ DROP EXTENSION injection_points;
+ DROP FUNCTION get_long_string();
+
+ 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_test;
+}
+# 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 c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ SELECT count(DISTINCT node) FROM relfilenodes;
+
+ INSERT INTO data_s1(i, j)
+ SELECT i, j FROM repack_test;
+
+ 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
+step change
+{
+ UPDATE repack_test SET j=get_long_string() where i=2;
+ DELETE FROM repack_test WHERE i=3;
+ INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+}
+# Check the table from the perspective of s2.
+step check2
+{
+ INSERT INTO relfilenodes(node)
+ SELECT c2.relfilenode
+ FROM pg_class c1 JOIN pg_class c2 ON c2.oid = c1.oid OR c2.oid = c1.reltoastrelid
+ WHERE c1.relname='repack_test';
+
+ INSERT INTO data_s2(i, j)
+ SELECT i, j FROM repack_test;
+}
+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
+ change
+ check2
+ wakeup_before_lock
+ check1
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index eb90fd3de5f..88da9ef75b4 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -2012,7 +2012,7 @@ pg_stat_progress_cluster| SELECT pid,
phase,
repack_index_relid AS cluster_index_relid,
heap_tuples_scanned,
- heap_tuples_written,
+ (heap_tuples_inserted + heap_tuples_updated) AS heap_tuples_written,
heap_blks_total,
heap_blks_scanned,
index_rebuild_count
@@ -2092,17 +2092,20 @@ pg_stat_progress_repack| SELECT s.pid,
WHEN 2 THEN 'index scanning heap'::text
WHEN 3 THEN 'sorting tuples'::text
WHEN 4 THEN 'writing new heap'::text
- WHEN 5 THEN 'swapping relation files'::text
- WHEN 6 THEN 'rebuilding index'::text
- WHEN 7 THEN 'performing final cleanup'::text
+ WHEN 5 THEN 'catch-up'::text
+ WHEN 6 THEN 'swapping relation files'::text
+ WHEN 7 THEN 'rebuilding index'::text
+ WHEN 8 THEN 'performing final cleanup'::text
ELSE NULL::text
END AS phase,
(s.param3)::oid AS repack_index_relid,
s.param4 AS heap_tuples_scanned,
- s.param5 AS heap_tuples_written,
- s.param6 AS heap_blks_total,
- s.param7 AS heap_blks_scanned,
- s.param8 AS index_rebuild_count
+ s.param5 AS heap_tuples_inserted,
+ s.param6 AS heap_tuples_updated,
+ s.param7 AS heap_tuples_deleted,
+ s.param8 AS heap_blks_total,
+ s.param9 AS heap_blks_scanned,
+ s.param10 AS index_rebuild_count
FROM (pg_stat_get_progress_info('REPACK'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
LEFT JOIN pg_database d ON ((s.datid = d.oid)));
pg_stat_progress_vacuum| SELECT s.pid,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 4f3c7c160a6..3139b14e85f 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -411,6 +411,7 @@ CatCacheHeader
CatalogId
CatalogIdMapEntry
CatalogIndexState
+ChangeDest
ChangeVarNodes_callback
ChangeVarNodes_context
CheckPoint
@@ -487,6 +488,8 @@ CompressFileHandle
CompressionLocation
CompressorState
ComputeXidHorizonsResult
+ConcurrentChange
+ConcurrentChangeKind
ConditionVariable
ConditionVariableMinimallyPadded
ConditionalStack
@@ -1264,6 +1267,7 @@ IndexElem
IndexFetchHeapData
IndexFetchTableData
IndexInfo
+IndexInsertState
IndexList
IndexOnlyScan
IndexOnlyScanState
@@ -2558,6 +2562,7 @@ ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepOriginId
RepackCommand
+RepackDecodingState
RepackStmt
ReparameterizeForeignPathByChild_function
ReplaceVarsFromTargetList_context
--
2.47.3
[text/x-diff] v28-0005-Use-background-worker-to-do-logical-decoding.patch (64.2K, ../210036.1765651719@localhost/6-v28-0005-Use-background-worker-to-do-logical-decoding.patch)
download | inline diff:
From 08c77f5c2ecc1890477fa460e4131b53538f6c42 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 5/6] Use background worker to do logical decoding.
If the backend performing REPACK (CONCURRENTLY) does both data copying and
logical decoding, it has to "travel in time" back and forth and therefore it
has to invalidate system caches quite a few times. (The copying and the
decoding work with different catalog snapshots.) As the decoding worker has
separate caches, the switching is not necessary.
Without the worker, it'd also be difficult to switch between potentiallly long
running tasks like index build and WAL decoding. (No decoding during that time
at all can suspend archiving / recycling of WAL segments for some time, which
in turn may result in full disk.)
Another problem is that, after having acquired AccessExclusiveLock (in order
to swap the files), the backend needs to both decode and apply the data
changes that took place while it was waiting for the lock. With the decoding
worker, the decoding runs all the time, so the backend only needs to apply the
changes. This can reduce the time the exclusive lock is held for.
Note that the code added in order to handle ERRORs in the background worker
almost duplicates the existing code that does the same for other types of
workers (See ProcessParallelMessages() and
ProcessParallelApplyMessages()). Refactoring of the existing code might be
useful, to reduce the duplication.
---
src/backend/access/heap/heapam_handler.c | 44 -
src/backend/commands/cluster.c | 1144 +++++++++++++----
src/backend/libpq/pqmq.c | 5 +
src/backend/postmaster/bgworker.c | 4 +
src/backend/replication/logical/logical.c | 6 +-
.../pgoutput_repack/pgoutput_repack.c | 54 +-
src/backend/storage/ipc/procsignal.c | 4 +
src/backend/tcop/postgres.c | 4 +
.../utils/activity/wait_event_names.txt | 2 +
src/include/access/tableam.h | 7 +-
src/include/commands/cluster.h | 68 +-
src/include/storage/procsignal.h | 1 +
src/tools/pgindent/typedefs.list | 4 +-
13 files changed, 946 insertions(+), 401 deletions(-)
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 6063e037edb..cb09e6fd1dc 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -33,7 +33,6 @@
#include "catalog/index.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
-#include "commands/cluster.h"
#include "commands/progress.h"
#include "executor/executor.h"
#include "miscadmin.h"
@@ -688,7 +687,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
Relation OldIndex, bool use_sort,
TransactionId OldestXmin,
Snapshot snapshot,
- LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -710,7 +708,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
BufferHeapTupleTableSlot *hslot;
BlockNumber prev_cblock = InvalidBlockNumber;
bool concurrent = snapshot != NULL;
- XLogRecPtr end_of_wal_prev = GetFlushRecPtr(NULL);
/* Remember if it's a system catalog */
is_system_catalog = IsSystemRelation(OldHeap);
@@ -957,31 +954,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
ct_val[1] = *num_tuples;
pgstat_progress_update_multi_param(2, ct_index, ct_val);
}
-
- /*
- * Process the WAL produced by the load, as well as by other
- * transactions, so that the replication slot can advance and WAL does
- * not pile up. Use wal_segment_size as a threshold so that we do not
- * introduce the decoding overhead too often.
- *
- * Of course, we must not apply the changes until the initial load has
- * completed.
- *
- * Note that our insertions into the new table should not be decoded
- * as we (intentionally) do not write the logical decoding specific
- * information to WAL.
- */
- if (concurrent)
- {
- XLogRecPtr end_of_wal;
-
- end_of_wal = GetFlushRecPtr(NULL);
- if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
- {
- repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
- end_of_wal_prev = end_of_wal;
- }
- }
}
if (indexScan != NULL)
@@ -1027,22 +999,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
/* Report n_tuples */
pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
n_tuples);
-
- /*
- * Try to keep the amount of not-yet-decoded WAL small, like
- * above.
- */
- if (concurrent)
- {
- XLogRecPtr end_of_wal;
-
- end_of_wal = GetFlushRecPtr(NULL);
- if ((end_of_wal - end_of_wal_prev) > wal_segment_size)
- {
- repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
- end_of_wal_prev = end_of_wal;
- }
- }
}
tuplesort_end(tuplesort);
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 569705abc81..b0383c1375f 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -12,12 +12,13 @@
* In concurrent mode, we lock the table with only ShareUpdateExclusiveLock,
* then do an initial copy as above. However, while the tuples are being
* copied, concurrent transactions could modify the table. To cope with those
- * changes, we rely on logical decoding to obtain them from WAL. The changes
- * are accumulated in a tuplestore. Once the initial copy is complete, we
- * read the changes from the tuplestore and re-apply them on the new heap.
- * Then we upgrade our ShareUpdateExclusiveLock to AccessExclusiveLock and
- * swap the relfilenodes. This way, the time we hold a strong lock on the
- * table is much reduced, and the bloat is eliminated.
+ * changes, we rely on logical decoding to obtain them from WAL. A bgworker
+ * consumes WAL while the initial copy is ongoing (to prevent excessive WAL
+ * from being reserved), and accumulates the changes in a file. Once the
+ * initial copy is complete, we read the changes from the file and re-apply
+ * them on the new heap. Then we upgrade our ShareUpdateExclusiveLock to
+ * AccessExclusiveLock and swap the relfilenodes. This way, the time we hold
+ * a strong lock on the table is much reduced, and the bloat is eliminated.
*
* There is hardly anything left of Paul Brown's original implementation...
*
@@ -61,6 +62,8 @@
#include "commands/tablecmds.h"
#include "commands/vacuum.h"
#include "executor/executor.h"
+#include "libpq/pqformat.h"
+#include "libpq/pqmq.h"
#include "miscadmin.h"
#include "optimizer/optimizer.h"
#include "pgstat.h"
@@ -71,6 +74,8 @@
#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
+#include "storage/procsignal.h"
+#include "tcop/tcopprot.h"
#include "utils/acl.h"
#include "utils/fmgroids.h"
#include "utils/guc.h"
@@ -138,6 +143,106 @@ typedef struct ChangeDest
IndexInsertState *iistate;
} ChangeDest;
+/*
+ * Layout of shared memory used for communication between backend and the
+ * worker that performs logical decoding of data changes
+ */
+typedef struct DecodingWorkerShared
+{
+ /* Is the decoding initialized? */
+ bool initialized;
+
+ /*
+ * Once the worker has reached this LSN, it should close the current
+ * output file and either create a new one or exit, according to the field
+ * 'done'. If the value is InvalidXLogRecPtr, the worker should decode all
+ * the WAL available and keep checking this field. It is ok if the worker
+ * had already decoded records whose LSN is >= lsn_upto before this field
+ * has been set.
+ */
+ XLogRecPtr lsn_upto;
+
+ /* Exit after closing the current file? */
+ bool done;
+
+ /* The output is stored here. */
+ SharedFileSet sfs;
+
+ /* Can backend read the file contents? */
+ bool sfs_valid;
+
+ /* Number of the last file exported by the worker. */
+ int last_exported;
+
+ /* Synchronize access to the fields above. */
+ slock_t mutex;
+
+ /* Database to connect to. */
+ Oid dbid;
+
+ /* Role to connect as. */
+ Oid roleid;
+
+ /* Decode data changes of this relation. */
+ Oid relid;
+
+ /* The backend uses this to wait for the worker. */
+ ConditionVariable cv;
+
+ /* Info to signal the backend. */
+ PGPROC *backend_proc;
+ pid_t backend_pid;
+ ProcNumber backend_proc_number;
+
+ /* Error queue. */
+ shm_mq *error_mq;
+
+ /*
+ * Memory the queue is located int.
+ *
+ * For considerations on the value see the comments of
+ * PARALLEL_ERROR_QUEUE_SIZE.
+ */
+#define REPACK_ERROR_QUEUE_SIZE 16384
+ char error_queue[FLEXIBLE_ARRAY_MEMBER];
+} DecodingWorkerShared;
+
+/*
+ * Generate worker's output file name. If relations of the same 'relid' happen
+ * to be processed at the same time, they must be from different databases and
+ * therefore different backends must be involved. (PID is already present in
+ * the fileset name.)
+ */
+static inline void
+DecodingWorkerFileName(char *fname, Oid relid, uint32 seq)
+{
+ snprintf(fname, MAXPGPATH, "%u-%u", relid, seq);
+}
+
+/*
+ * Backend-local information to control the decoding worker.
+ */
+typedef struct DecodingWorker
+{
+ /* The worker. */
+ BackgroundWorkerHandle *handle;
+
+ /* DecodingWorkerShared is in this segment. */
+ dsm_segment *seg;
+
+ /* Handle of the error queue. */
+ shm_mq_handle *error_mqh;
+} DecodingWorker;
+
+/* Pointer to currently running decoding worker. */
+static DecodingWorker *decoding_worker = NULL;
+
+/*
+ * Is there a message sent by a repack worker that the backend needs to
+ * receive?
+ */
+volatile sig_atomic_t RepackMessagePending = false;
+
static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap,
Oid indexOid, Oid userid, LOCKMODE lmode,
int options);
@@ -145,7 +250,7 @@ static void check_repack_concurrently_requirements(Relation rel);
static void rebuild_relation(Relation OldHeap, Relation index, bool verbose,
bool concurrent);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
+ Snapshot snapshot,
bool verbose,
bool *pSwapToastByContent,
TransactionId *pFreezeXid,
@@ -158,12 +263,10 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
static bool cluster_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
-static void begin_concurrent_repack(Relation rel);
-static void end_concurrent_repack(void);
static LogicalDecodingContext *setup_logical_decoding(Oid relid);
-static HeapTuple get_changed_tuple(char *change);
-static void apply_concurrent_changes(RepackDecodingState *dstate,
- ChangeDest *dest);
+static bool decode_concurrent_changes(LogicalDecodingContext *ctx,
+ DecodingWorkerShared *shared);
+static void apply_concurrent_changes(BufFile *file, ChangeDest *dest);
static void apply_concurrent_insert(Relation rel, HeapTuple tup,
IndexInsertState *iistate,
TupleTableSlot *index_slot);
@@ -175,9 +278,9 @@ static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
HeapTuple tup_key,
TupleTableSlot *ident_slot);
-static void process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
- XLogRecPtr end_of_wal,
- ChangeDest *dest);
+static void process_concurrent_changes(XLogRecPtr end_of_wal,
+ ChangeDest *dest,
+ bool done);
static IndexInsertState *get_index_insert_state(Relation relation,
Oid ident_index_id,
Relation *ident_index_p);
@@ -187,7 +290,6 @@ static void free_index_insert_state(IndexInsertState *iistate);
static void cleanup_logical_decoding(LogicalDecodingContext *ctx);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
- LogicalDecodingContext *decoding_ctx,
TransactionId frozenXid,
MultiXactId cutoffMulti);
static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes);
@@ -197,6 +299,13 @@ static Relation process_single_relation(RepackStmt *stmt,
ClusterParams *params);
static Oid determine_clustered_index(Relation rel, bool usingindex,
const char *indexname);
+static void start_decoding_worker(Oid relid);
+static void stop_decoding_worker(void);
+static void repack_worker_internal(dsm_segment *seg);
+static void export_initial_snapshot(Snapshot snapshot,
+ DecodingWorkerShared *shared);
+static Snapshot get_initial_snapshot(DecodingWorker *worker);
+static void ProcessRepackMessage(StringInfo msg);
static const char *RepackCommandAsString(RepackCommand cmd);
@@ -619,20 +728,20 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid,
/* rebuild_relation does all the dirty work */
PG_TRY();
{
- /*
- * For concurrent processing, make sure that our logical decoding
- * ignores data changes of other tables than the one we are
- * processing.
- */
- if (concurrent)
- begin_concurrent_repack(OldHeap);
-
rebuild_relation(OldHeap, index, verbose, concurrent);
}
PG_FINALLY();
{
if (concurrent)
- end_concurrent_repack();
+ {
+ /*
+ * Since during normal operation the worker was already asked to
+ * exit, stopping it explicitly is especially important on ERROR.
+ * However it still seems a good practice to make sure that the
+ * worker never survives the REPACK command.
+ */
+ stop_decoding_worker();
+ }
}
PG_END_TRY();
@@ -929,7 +1038,6 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
bool swap_toast_by_content;
TransactionId frozenXid;
MultiXactId cutoffMulti;
- LogicalDecodingContext *decoding_ctx = NULL;
Snapshot snapshot = NULL;
#if USE_ASSERT_CHECKING
LOCKMODE lmode;
@@ -943,19 +1051,36 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
if (concurrent)
{
/*
- * Prepare to capture the concurrent data changes.
+ * The worker needs to be member of the locking group we're the leader
+ * of. We ought to become the leader before the worker starts. The
+ * worker will join the group as soon as it starts.
+ *
+ * This is to make sure that the deadlock described below is
+ * detectable by deadlock.c: if the worker waits for a transaction to
+ * complete and we are waiting for the worker output, then effectively
+ * we (i.e. this backend) are waiting for that transaction.
+ */
+ BecomeLockGroupLeader();
+
+ /*
+ * Start the worker that decodes data changes applied while we're
+ * copying the table contents.
*
- * Note that this call waits 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 its still eligible for REPACK
- * CONCURRENTLY.
+ * 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 its still eligible for
+ * REPACK CONCURRENTLY.
+ */
+ start_decoding_worker(tableOid);
+
+ /*
+ * Wait until the worker has the initial snapshot and retrieve it.
*/
- decoding_ctx = setup_logical_decoding(tableOid);
+ snapshot = get_initial_snapshot(decoding_worker);
- snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
PushActiveSnapshot(snapshot);
}
@@ -980,7 +1105,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
NewHeap = table_open(OIDNewHeap, NoLock);
/* Copy the heap data into the new table in the desired order */
- copy_table_data(NewHeap, OldHeap, index, snapshot, decoding_ctx, verbose,
+ copy_table_data(NewHeap, OldHeap, index, snapshot, verbose,
&swap_toast_by_content, &frozenXid, &cutoffMulti);
/* The historic snapshot won't be needed anymore. */
@@ -994,14 +1119,10 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
{
Assert(!swap_toast_by_content);
rebuild_relation_finish_concurrent(NewHeap, OldHeap, index,
- decoding_ctx,
frozenXid, cutoffMulti);
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
-
- /* Done with decoding. */
- cleanup_logical_decoding(decoding_ctx);
}
else
{
@@ -1172,8 +1293,7 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
*/
static void
copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot, LogicalDecodingContext *decoding_ctx,
- bool verbose, bool *pSwapToastByContent,
+ Snapshot snapshot, bool verbose, bool *pSwapToastByContent,
TransactionId *pFreezeXid, MultiXactId *pCutoffMulti)
{
Relation relRelation;
@@ -1334,7 +1454,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
*/
table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort,
cutoffs.OldestXmin, snapshot,
- decoding_ctx,
&cutoffs.FreezeLimit,
&cutoffs.MultiXactCutoff,
&num_tuples, &tups_vacuumed,
@@ -2367,59 +2486,6 @@ RepackCommandAsString(RepackCommand cmd)
return "???";
}
-
-/*
- * Call this function before REPACK CONCURRENTLY starts to setup logical
- * decoding. It makes sure that other users of the table put enough
- * information into WAL.
- *
- * The point is that at various places we expect that the table we're
- * processing is treated like a system catalog. For example, we need to be
- * able to scan it using a "historic snapshot" anytime during the processing
- * (as opposed to scanning only at the start point of the decoding, as logical
- * replication does during initial table synchronization), in order to apply
- * concurrent UPDATE / DELETE commands.
- *
- * Note that TOAST table needs no attention here as it's not scanned using
- * historic snapshot.
- */
-static void
-begin_concurrent_repack(Relation rel)
-{
- Oid toastrelid;
-
- /*
- * Avoid logical decoding of other relations by this backend. The lock we
- * have guarantees that the actual locator cannot be changed concurrently:
- * TRUNCATE needs AccessExclusiveLock.
- */
- Assert(CheckRelationLockedByMe(rel, ShareUpdateExclusiveLock, false));
- repacked_rel_locator = rel->rd_locator;
- toastrelid = rel->rd_rel->reltoastrelid;
- if (OidIsValid(toastrelid))
- {
- Relation toastrel;
-
- /* Avoid logical decoding of other TOAST relations. */
- toastrel = table_open(toastrelid, AccessShareLock);
- repacked_rel_toast_locator = toastrel->rd_locator;
- table_close(toastrel, AccessShareLock);
- }
-}
-
-/*
- * Call this when done with REPACK CONCURRENTLY.
- */
-static void
-end_concurrent_repack(void)
-{
- /*
- * Restore normal function of (future) logical decoding for this backend.
- */
- repacked_rel_locator.relNumber = InvalidOid;
- repacked_rel_toast_locator.relNumber = InvalidOid;
-}
-
/*
* This function is much like pg_create_logical_replication_slot() except that
* the new slot is neither released (if anyone else could read changes from
@@ -2431,9 +2497,10 @@ static LogicalDecodingContext *
setup_logical_decoding(Oid relid)
{
Relation rel;
- TupleDesc tupdesc;
+ Oid toastrelid;
LogicalDecodingContext *ctx;
- RepackDecodingState *dstate = palloc0_object(RepackDecodingState);
+ NameData slotname;
+ RepackDecodingState *dstate;
/*
* REPACK CONCURRENTLY is not allowed in a transaction block, so this
@@ -2441,21 +2508,21 @@ setup_logical_decoding(Oid relid)
*/
Assert(!TransactionIdIsValid(GetTopTransactionIdIfAny()));
- /*
- * A single backend should not execute multiple REPACK commands at a time,
- * so use PID to make the slot unique.
- */
- snprintf(NameStr(dstate->slotname), NAMEDATALEN, "repack_%d", MyProcPid);
-
/*
* Check if we can use logical decoding.
*/
CheckSlotPermissions();
CheckLogicalDecodingRequirements();
- /* RS_TEMPORARY so that the slot gets cleaned up on ERROR. */
- ReplicationSlotCreate(NameStr(dstate->slotname), true, RS_TEMPORARY,
- false, false, false);
+ /*
+ * A single backend should not execute multiple REPACK commands at a time,
+ * so use PID to make the slot unique.
+ *
+ * RS_TEMPORARY so that the slot gets cleaned up on ERROR.
+ */
+ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid);
+ ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false,
+ false);
/*
* Neither prepare_write nor do_write callback nor update_progress is
@@ -2477,104 +2544,109 @@ setup_logical_decoding(Oid relid)
DecodingContextFindStartpoint(ctx);
+ /*
+ * decode_concurrent_changes() needs non-blocking callback.
+ */
+ ctx->reader->routine.page_read = read_local_xlog_page_no_wait;
+
+ /*
+ * read_local_xlog_page_no_wait() needs to be able to indicate the end of
+ * WAL.
+ */
+ ctx->reader->private_data = MemoryContextAllocZero(ctx->context,
+ sizeof(ReadLocalXLogPageNoWaitPrivate));
+
+
/* Some WAL records should have been read. */
Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr);
+ /*
+ * Initialize repack_current_segment so that we can notice WAL segment
+ * boundaries.
+ */
XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment,
wal_segment_size);
- /*
- * Setup structures to store decoded changes.
- */
+ dstate = palloc0_object(RepackDecodingState);
dstate->relid = relid;
- dstate->tstore = tuplestore_begin_heap(false, false,
- maintenance_work_mem);
- /* Caller should already have the table locked. */
- rel = table_open(relid, NoLock);
- tupdesc = CreateTupleDescCopy(RelationGetDescr(rel));
- dstate->tupdesc = tupdesc;
- table_close(rel, NoLock);
+ /*
+ * Tuple descriptor may be needed to flatten a tuple before we write it to
+ * a file. A copy is needed because the decoding worker invalidates system
+ * caches before it starts to do the actual work.
+ */
+ rel = table_open(relid, AccessShareLock);
+ dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel));
- /* Initialize the descriptor to store the changes ... */
- dstate->tupdesc_change = CreateTemplateTupleDesc(1);
+ /* Avoid logical decoding of other relations. */
+ repacked_rel_locator = rel->rd_locator;
+ toastrelid = rel->rd_rel->reltoastrelid;
+ if (OidIsValid(toastrelid))
+ {
+ Relation toastrel;
- TupleDescInitEntry(dstate->tupdesc_change, 1, NULL, BYTEAOID, -1, 0);
- /* ... as well as the corresponding slot. */
- dstate->tsslot = MakeSingleTupleTableSlot(dstate->tupdesc_change,
- &TTSOpsMinimalTuple);
+ /* Avoid logical decoding of other TOAST relations. */
+ toastrel = table_open(toastrelid, AccessShareLock);
+ repacked_rel_toast_locator = toastrel->rd_locator;
+ table_close(toastrel, AccessShareLock);
+ }
+ table_close(rel, AccessShareLock);
- dstate->resowner = ResourceOwnerCreate(CurrentResourceOwner,
- "logical decoding");
+ /* The file will be set as soon as we have it opened. */
+ dstate->file = NULL;
ctx->output_writer_private = dstate;
+
return ctx;
}
/*
- * Retrieve tuple from ConcurrentChange structure.
+ * Decode logical changes from the WAL sequence and store them to a file.
*
- * The input data starts with the structure but it might not be appropriately
- * aligned.
+ * If true is returned, there is no more work for the worker.
*/
-static HeapTuple
-get_changed_tuple(char *change)
-{
- HeapTupleData tup_data;
- HeapTuple result;
- char *src;
-
- /*
- * Ensure alignment before accessing the fields. (This is why we can't use
- * heap_copytuple() instead of this function.)
- */
- src = change + offsetof(ConcurrentChange, tup_data);
- memcpy(&tup_data, src, sizeof(HeapTupleData));
-
- result = (HeapTuple) palloc(HEAPTUPLESIZE + tup_data.t_len);
- memcpy(result, &tup_data, sizeof(HeapTupleData));
- result->t_data = (HeapTupleHeader) ((char *) result + HEAPTUPLESIZE);
- src = change + SizeOfConcurrentChange;
- memcpy(result->t_data, src, result->t_len);
-
- return result;
-}
-
-/*
- * Decode logical changes from the WAL sequence up to end_of_wal.
- */
-void
-repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
- XLogRecPtr end_of_wal)
+static bool
+decode_concurrent_changes(LogicalDecodingContext *ctx,
+ DecodingWorkerShared *shared)
{
RepackDecodingState *dstate;
- ResourceOwner resowner_old;
+ XLogRecPtr lsn_upto;
+ bool done;
+ char fname[MAXPGPATH];
dstate = (RepackDecodingState *) ctx->output_writer_private;
- resowner_old = CurrentResourceOwner;
- CurrentResourceOwner = dstate->resowner;
- PG_TRY();
+ /* Open the output file. */
+ DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ dstate->file = BufFileCreateFileSet(&shared->sfs.fs, fname);
+
+ SpinLockAcquire(&shared->mutex);
+ lsn_upto = shared->lsn_upto;
+ done = shared->done;
+ SpinLockRelease(&shared->mutex);
+
+ while (true)
{
- while (ctx->reader->EndRecPtr < end_of_wal)
- {
- XLogRecord *record;
- XLogSegNo segno_new;
- char *errm = NULL;
- XLogRecPtr end_lsn;
+ XLogRecord *record;
+ XLogSegNo segno_new;
+ char *errm = NULL;
+ XLogRecPtr end_lsn;
- record = XLogReadRecord(ctx->reader, &errm);
- if (errm)
- elog(ERROR, "%s", errm);
+ CHECK_FOR_INTERRUPTS();
- if (record != NULL)
- LogicalDecodingProcessRecord(ctx, ctx->reader);
+ record = XLogReadRecord(ctx->reader, &errm);
+ if (record)
+ {
+ LogicalDecodingProcessRecord(ctx, ctx->reader);
/*
* If WAL segment boundary has been crossed, inform the decoding
- * system that the catalog_xmin can advance. (We can confirm more
- * often, but a filling a single WAL segment should not take much
- * time.)
+ * system that the catalog_xmin can advance.
+ *
+ * TODO Does it make sense to confirm more often? Segment size
+ * seems appropriate for restart_lsn (because less than a segment
+ * cannot be recycled anyway), however more frequent checks might
+ * be beneficial for catalog_xmin.
*/
end_lsn = ctx->reader->EndRecPtr;
XLByteToSeg(end_lsn, segno_new, wal_segment_size);
@@ -2585,80 +2657,117 @@ repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
(uint32) (end_lsn >> 32), (uint32) end_lsn);
repack_current_segment = segno_new;
}
+ }
+ else
+ {
+ ReadLocalXLogPageNoWaitPrivate *priv;
+
+ if (errm)
+ ereport(ERROR, (errmsg("%s", errm)));
- CHECK_FOR_INTERRUPTS();
+ /*
+ * In the decoding loop we do not want to get blocked when there
+ * is no more WAL available, otherwise the loop would become
+ * uninterruptible. The point is that the worker is only useful if
+ * it starts decoding before lsn_upto is set. Thus it can reach
+ * the end of WAL and find out later that it did not have to go
+ * that far.
+ */
+ priv = (ReadLocalXLogPageNoWaitPrivate *)
+ ctx->reader->private_data;
+ if (priv->end_of_wal)
+ priv->end_of_wal = false;
+ else
+ ereport(ERROR, (errmsg("could not read WAL record")));
}
- InvalidateSystemCaches();
- CurrentResourceOwner = resowner_old;
- }
- PG_CATCH();
- {
- /* clear all timetravel entries */
- InvalidateSystemCaches();
- CurrentResourceOwner = resowner_old;
- PG_RE_THROW();
+
+ /*
+ * Whether we could read new record or not, keep checking if
+ * 'lsn_upto' was specified.
+ */
+ if (XLogRecPtrIsInvalid(lsn_upto))
+ {
+ SpinLockAcquire(&shared->mutex);
+ lsn_upto = shared->lsn_upto;
+ /* 'done' should be set at the same time as 'lsn_upto' */
+ done = shared->done;
+ SpinLockRelease(&shared->mutex);
+ }
+ if (!XLogRecPtrIsInvalid(lsn_upto) &&
+ ctx->reader->EndRecPtr >= lsn_upto)
+ break;
+
+ if (record == NULL)
+ /* Wait a bit before we retry reading WAL. */
+ (void) WaitLatch(MyLatch,
+ WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+ 100000L, /* XXX Tune the delay. */
+ WAIT_EVENT_REPACK_WORKER_MAIN);
}
- PG_END_TRY();
+
+ /*
+ * Close the file so we can make it available to the backend.
+ */
+ BufFileClose(dstate->file);
+ dstate->file = NULL;
+ SpinLockAcquire(&shared->mutex);
+ shared->lsn_upto = InvalidXLogRecPtr;
+ shared->sfs_valid = true;
+ shared->last_exported++;
+ SpinLockRelease(&shared->mutex);
+ ConditionVariableSignal(&shared->cv);
+
+ return done;
}
/*
* Apply changes stored in 'file'.
*/
static void
-apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
+apply_concurrent_changes(BufFile *file, ChangeDest *dest)
{
+ char kind;
+ uint32 t_len;
Relation rel = dest->rel;
TupleTableSlot *index_slot,
*ident_slot;
HeapTuple tup_old = NULL;
- if (dstate->nchanges == 0)
- return;
-
/* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
- index_slot = MakeSingleTupleTableSlot(dstate->tupdesc, &TTSOpsHeapTuple);
+ index_slot = MakeSingleTupleTableSlot(RelationGetDescr(rel),
+ &TTSOpsHeapTuple);
/* A slot to fetch tuples from identity index. */
ident_slot = table_slot_create(rel, NULL);
- while (tuplestore_gettupleslot(dstate->tstore, true, false,
- dstate->tsslot))
+ while (true)
{
- bool shouldFree;
- HeapTuple tup_change,
- tup,
+ size_t nread;
+ HeapTuple tup,
tup_exist;
- char *change_raw,
- *src;
- ConcurrentChange change;
- bool isnull[1];
- Datum values[1];
CHECK_FOR_INTERRUPTS();
- /* Get the change from the single-column tuple. */
- tup_change = ExecFetchSlotHeapTuple(dstate->tsslot, false, &shouldFree);
- heap_deform_tuple(tup_change, dstate->tupdesc_change, values, isnull);
- Assert(!isnull[0]);
-
- /* Make sure we access aligned data. */
- change_raw = (char *) DatumGetByteaP(values[0]);
- src = (char *) VARDATA(change_raw);
- memcpy(&change, src, SizeOfConcurrentChange);
+ nread = BufFileReadMaybeEOF(file, &kind, 1, true);
+ /* Are we done with the file? */
+ if (nread == 0)
+ break;
- /*
- * Extract the tuple from the change. The tuple is copied here because
- * it might be assigned to 'tup_old', in which case it needs to
- * survive into the next iteration.
- */
- tup = get_changed_tuple(src);
+ /* Read the tuple. */
+ BufFileReadExact(file, &t_len, sizeof(t_len));
+ tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len);
+ tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE);
+ BufFileReadExact(file, tup->t_data, t_len);
+ tup->t_len = t_len;
+ ItemPointerSetInvalid(&tup->t_self);
+ tup->t_tableOid = RelationGetRelid(dest->rel);
- if (change.kind == CHANGE_UPDATE_OLD)
+ if (kind == CHANGE_UPDATE_OLD)
{
Assert(tup_old == NULL);
tup_old = tup;
}
- else if (change.kind == CHANGE_INSERT)
+ else if (kind == CHANGE_INSERT)
{
Assert(tup_old == NULL);
@@ -2666,12 +2775,11 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
pfree(tup);
}
- else if (change.kind == CHANGE_UPDATE_NEW ||
- change.kind == CHANGE_DELETE)
+ else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE)
{
HeapTuple tup_key;
- if (change.kind == CHANGE_UPDATE_NEW)
+ if (kind == CHANGE_UPDATE_NEW)
{
tup_key = tup_old != NULL ? tup_old : tup;
}
@@ -2688,7 +2796,7 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
if (tup_exist == NULL)
elog(ERROR, "failed to find target tuple");
- if (change.kind == CHANGE_UPDATE_NEW)
+ if (kind == CHANGE_UPDATE_NEW)
apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
index_slot);
else
@@ -2703,26 +2811,19 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest)
pfree(tup);
}
else
- elog(ERROR, "unrecognized kind of change: %d", change.kind);
+ elog(ERROR, "unrecognized kind of change: %d", kind);
/*
* If a change was applied now, increment CID for next writes and
* update the snapshot so it sees the changes we've applied so far.
*/
- if (change.kind != CHANGE_UPDATE_OLD)
+ if (kind != CHANGE_UPDATE_OLD)
{
CommandCounterIncrement();
UpdateActiveSnapshotCommandId();
}
-
- /* TTSOpsMinimalTuple has .get_heap_tuple==NULL. */
- Assert(shouldFree);
- pfree(tup_change);
}
- tuplestore_clear(dstate->tstore);
- dstate->nchanges = 0;
-
/* Cleanup. */
ExecDropSingleTupleTableSlot(index_slot);
ExecDropSingleTupleTableSlot(ident_slot);
@@ -2901,25 +3002,58 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
}
/*
- * Decode and apply concurrent changes.
+ * Decode and apply concurrent changes, up to (and including) the record whose
+ * LSN is 'end_of_wal'.
*/
static void
-process_concurrent_changes(LogicalDecodingContext *decoding_ctx,
- XLogRecPtr end_of_wal, ChangeDest *dest)
+process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
{
- RepackDecodingState *dstate;
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_CATCH_UP);
- dstate = (RepackDecodingState *) decoding_ctx->output_writer_private;
+ /* Ask the worker for the file. */
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+ SpinLockAcquire(&shared->mutex);
+ shared->lsn_upto = end_of_wal;
+ shared->done = done;
+ SpinLockRelease(&shared->mutex);
- repack_decode_concurrent_changes(decoding_ctx, end_of_wal);
+ /*
+ * The worker needs to finish processing of the current WAL record. Even
+ * if it's idle, it'll need to close the output file. Thus we're likely to
+ * wait, so prepare for sleep.
+ */
+ ConditionVariablePrepareToSleep(&shared->cv);
+ for (;;)
+ {
+ bool valid;
- if (dstate->nchanges == 0)
- return;
+ SpinLockAcquire(&shared->mutex);
+ valid = shared->sfs_valid;
+ SpinLockRelease(&shared->mutex);
+
+ if (valid)
+ break;
+
+ ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
+ }
+ ConditionVariableCancelSleep();
- apply_concurrent_changes(dstate, dest);
+ /* Open the file. */
+ DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
+ apply_concurrent_changes(file, dest);
+
+ /* No file is exported until the worker exports the next one. */
+ SpinLockAcquire(&shared->mutex);
+ shared->sfs_valid = false;
+ SpinLockRelease(&shared->mutex);
+
+ BufFileClose(file);
}
/*
@@ -3045,15 +3179,10 @@ cleanup_logical_decoding(LogicalDecodingContext *ctx)
dstate = (RepackDecodingState *) ctx->output_writer_private;
- ExecDropSingleTupleTableSlot(dstate->tsslot);
- FreeTupleDesc(dstate->tupdesc_change);
FreeTupleDesc(dstate->tupdesc);
- tuplestore_end(dstate->tstore);
-
FreeDecodingContext(ctx);
- ReplicationSlotRelease();
- ReplicationSlotDrop(NameStr(dstate->slotname), false);
+ ReplicationSlotDropAcquired();
pfree(dstate);
}
@@ -3068,7 +3197,6 @@ cleanup_logical_decoding(LogicalDecodingContext *ctx)
static void
rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
- LogicalDecodingContext *decoding_ctx,
TransactionId frozenXid,
MultiXactId cutoffMulti)
{
@@ -3172,7 +3300,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
* hold AccessExclusiveLock. (Quite some amount of WAL could have been
* written during the data copying and index creation.)
*/
- process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+ process_concurrent_changes(end_of_wal, &chgdst, false);
/*
* Acquire AccessExclusiveLock on the table, its TOAST relation (if there
@@ -3268,8 +3396,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
XLogFlush(wal_insert_ptr);
end_of_wal = GetFlushRecPtr(NULL);
- /* Apply the concurrent changes again. */
- process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst);
+ /*
+ * Apply the concurrent changes again. Indicate that the decoding worker
+ * won't be needed anymore.
+ */
+ process_concurrent_changes(end_of_wal, &chgdst, true);
/* Remember info about rel before closing OldHeap */
relpersistence = OldHeap->rd_rel->relpersistence;
@@ -3382,3 +3513,514 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
return result;
}
+
+/*
+ * Try to start a background worker to perform logical decoding of data
+ * changes applied to relation while REPACK CONCURRENTLY is copying its
+ * contents to a new table.
+ */
+static void
+start_decoding_worker(Oid relid)
+{
+ Size size;
+ dsm_segment *seg;
+ DecodingWorkerShared *shared;
+ shm_mq *mq;
+ shm_mq_handle *mqh;
+ BackgroundWorker bgw;
+
+ /* Setup shared memory. */
+ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
+ BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
+ seg = dsm_create(size, 0);
+ shared = (DecodingWorkerShared *) dsm_segment_address(seg);
+ shared->lsn_upto = InvalidXLogRecPtr;
+ shared->done = false;
+ SharedFileSetInit(&shared->sfs, seg);
+ shared->sfs_valid = false;
+ shared->last_exported = -1;
+ SpinLockInit(&shared->mutex);
+ shared->dbid = MyDatabaseId;
+
+ /*
+ * This is the UserId set in cluster_rel(). Security context shouldn't be
+ * needed for decoding worker.
+ */
+ shared->roleid = GetUserId();
+ shared->relid = relid;
+ ConditionVariableInit(&shared->cv);
+ shared->backend_proc = MyProc;
+ shared->backend_pid = MyProcPid;
+ shared->backend_proc_number = MyProcNumber;
+
+ mq = shm_mq_create((char *) BUFFERALIGN(shared->error_queue),
+ REPACK_ERROR_QUEUE_SIZE);
+ shm_mq_set_receiver(mq, MyProc);
+ mqh = shm_mq_attach(mq, seg, NULL);
+
+ memset(&bgw, 0, sizeof(bgw));
+ snprintf(bgw.bgw_name, BGW_MAXLEN,
+ "REPACK decoding worker for relation \"%s\"",
+ get_rel_name(relid));
+ snprintf(bgw.bgw_type, BGW_MAXLEN, "REPACK decoding worker");
+ bgw.bgw_flags = BGWORKER_SHMEM_ACCESS |
+ BGWORKER_BACKEND_DATABASE_CONNECTION;
+ bgw.bgw_start_time = BgWorkerStart_RecoveryFinished;
+ bgw.bgw_restart_time = BGW_NEVER_RESTART;
+ snprintf(bgw.bgw_library_name, MAXPGPATH, "postgres");
+ snprintf(bgw.bgw_function_name, BGW_MAXLEN, "RepackWorkerMain");
+ bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
+ bgw.bgw_notify_pid = MyProcPid;
+
+ decoding_worker = palloc0_object(DecodingWorker);
+ if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
+ ereport(ERROR,
+ (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
+ errmsg("out of background worker slots"),
+ errhint("You might need to increase \"%s\".", "max_worker_processes")));
+
+ decoding_worker->seg = seg;
+ decoding_worker->error_mqh = mqh;
+
+ /*
+ * 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.
+ */
+ ConditionVariablePrepareToSleep(&shared->cv);
+ for (;;)
+ {
+ int initialized;
+
+ SpinLockAcquire(&shared->mutex);
+ initialized = shared->initialized;
+ SpinLockRelease(&shared->mutex);
+
+ if (initialized)
+ break;
+
+ ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
+ }
+ ConditionVariableCancelSleep();
+}
+
+/*
+ * Stop the decoding worker and cleanup the related resources.
+ *
+ * The worker stops on its own when it knows there is no more work to do, but
+ * we need to stop it explicitly at least on ERROR in the launching backend.
+ */
+static void
+stop_decoding_worker(void)
+{
+ BgwHandleStatus status;
+
+ /* Haven't reached the worker startup? */
+ if (decoding_worker == NULL)
+ return;
+
+ /* Could not register the worker? */
+ if (decoding_worker->handle == NULL)
+ return;
+
+ TerminateBackgroundWorker(decoding_worker->handle);
+ /* The worker should really exit before the REPACK command does. */
+ HOLD_INTERRUPTS();
+ status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+ RESUME_INTERRUPTS();
+
+ if (status == BGWH_POSTMASTER_DIED)
+ ereport(FATAL,
+ (errcode(ERRCODE_ADMIN_SHUTDOWN),
+ errmsg("postmaster exited during REPACK command")));
+
+ shm_mq_detach(decoding_worker->error_mqh);
+
+ /*
+ * If we could not cancel the current sleep due to ERROR, do that before
+ * we detach from the shared memory the condition variable is located in.
+ * If we did not, the bgworker ERROR handling code would try and fail
+ * badly.
+ */
+ ConditionVariableCancelSleep();
+
+ dsm_detach(decoding_worker->seg);
+ pfree(decoding_worker);
+ decoding_worker = NULL;
+}
+
+/* Is this process a REPACK worker? */
+static bool is_repack_worker = false;
+
+static pid_t backend_pid;
+static ProcNumber backend_proc_number;
+
+/*
+ * See ParallelWorkerShutdown for details.
+ */
+static void
+RepackWorkerShutdown(int code, Datum arg)
+{
+ SendProcSignal(backend_pid,
+ PROCSIG_REPACK_MESSAGE,
+ backend_proc_number);
+
+ dsm_detach((dsm_segment *) DatumGetPointer(arg));
+}
+
+/* REPACK decoding worker entry point */
+void
+RepackWorkerMain(Datum main_arg)
+{
+ dsm_segment *seg;
+ DecodingWorkerShared *shared;
+ shm_mq *mq;
+ shm_mq_handle *mqh;
+
+ is_repack_worker = true;
+
+ /*
+ * Override the default bgworker_die() with die() so we can use
+ * CHECK_FOR_INTERRUPTS().
+ */
+ pqsignal(SIGTERM, die);
+ BackgroundWorkerUnblockSignals();
+
+ seg = dsm_attach(DatumGetUInt32(main_arg));
+ if (seg == NULL)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("could not map dynamic shared memory segment")));
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(seg);
+
+ /* Arrange to signal the leader if we exit. */
+ backend_pid = shared->backend_pid;
+ backend_proc_number = shared->backend_proc_number;
+ before_shmem_exit(RepackWorkerShutdown, PointerGetDatum(seg));
+
+ /*
+ * Join locking group - see the comments around the call of
+ * start_decoding_worker().
+ */
+ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid))
+ /* The leader is not running anymore. */
+ return;
+
+ /*
+ * Setup a queue to send error messages to the backend that launched this
+ * worker.
+ */
+ mq = (shm_mq *) (char *) BUFFERALIGN(shared->error_queue);
+ shm_mq_set_sender(mq, MyProc);
+ mqh = shm_mq_attach(mq, seg, NULL);
+ pq_redirect_to_shm_mq(seg, mqh);
+ pq_set_parallel_leader(shared->backend_pid,
+ shared->backend_proc_number);
+
+ /* Connect to the database. */
+ BackgroundWorkerInitializeConnectionByOid(shared->dbid, shared->roleid, 0);
+
+ repack_worker_internal(seg);
+}
+
+static void
+repack_worker_internal(dsm_segment *seg)
+{
+ DecodingWorkerShared *shared;
+ LogicalDecodingContext *decoding_ctx;
+ SharedFileSet *sfs;
+ Snapshot snapshot;
+
+ /*
+ * Transaction is needed to open relation, and it also provides us with a
+ * resource owner.
+ */
+ StartTransactionCommand();
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(seg);
+
+ /*
+ * Not sure the spinlock is needed here - the backend should not change
+ * anything in the shared memory until we have serialized the snapshot.
+ */
+ SpinLockAcquire(&shared->mutex);
+ Assert(XLogRecPtrIsInvalid(shared->lsn_upto));
+ Assert(!shared->sfs_valid);
+ sfs = &shared->sfs;
+ SpinLockRelease(&shared->mutex);
+
+ SharedFileSetAttach(sfs, seg);
+
+ /*
+ * Prepare to capture the concurrent data changes ourselves.
+ */
+ decoding_ctx = setup_logical_decoding(shared->relid);
+
+ /* Announce that we're ready. */
+ SpinLockAcquire(&shared->mutex);
+ shared->initialized = true;
+ SpinLockRelease(&shared->mutex);
+ ConditionVariableSignal(&shared->cv);
+
+ /* Build the initial snapshot and export it. */
+ snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
+ export_initial_snapshot(snapshot, shared);
+
+ /*
+ * Only historic snapshots should be used now. Do not let us restrict the
+ * progress of xmin horizon.
+ */
+ InvalidateCatalogSnapshot();
+
+ while (!decode_concurrent_changes(decoding_ctx, shared))
+ ;
+
+ /* Cleanup. */
+ cleanup_logical_decoding(decoding_ctx);
+ CommitTransactionCommand();
+}
+
+/*
+ * Make snapshot available to the backend that launched the decoding worker.
+ */
+static void
+export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
+{
+ char fname[MAXPGPATH];
+ BufFile *file;
+ Size snap_size;
+ char *snap_space;
+
+ snap_size = EstimateSnapshotSpace(snapshot);
+ snap_space = (char *) palloc(snap_size);
+ SerializeSnapshot(snapshot, snap_space);
+ FreeSnapshot(snapshot);
+
+ DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ file = BufFileCreateFileSet(&shared->sfs.fs, fname);
+ /* To make restoration easier, write the snapshot size first. */
+ BufFileWrite(file, &snap_size, sizeof(snap_size));
+ BufFileWrite(file, snap_space, snap_size);
+ pfree(snap_space);
+ BufFileClose(file);
+
+ /* Tell the backend that the file is available. */
+ SpinLockAcquire(&shared->mutex);
+ shared->sfs_valid = true;
+ shared->last_exported++;
+ SpinLockRelease(&shared->mutex);
+ ConditionVariableSignal(&shared->cv);
+}
+
+/*
+ * Get the initial snapshot from the decoding worker.
+ */
+static Snapshot
+get_initial_snapshot(DecodingWorker *worker)
+{
+ DecodingWorkerShared *shared;
+ char fname[MAXPGPATH];
+ BufFile *file;
+ Size snap_size;
+ char *snap_space;
+ Snapshot snapshot;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(worker->seg);
+
+ /*
+ * The worker needs to initialize the logical decoding, which usually
+ * takes some time. Therefore it makes sense to prepare for the sleep
+ * first.
+ */
+ ConditionVariablePrepareToSleep(&shared->cv);
+ for (;;)
+ {
+ bool valid;
+
+ SpinLockAcquire(&shared->mutex);
+ valid = shared->sfs_valid;
+ SpinLockRelease(&shared->mutex);
+
+ if (valid)
+ break;
+
+ ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
+ }
+ ConditionVariableCancelSleep();
+
+ /* Read the snapshot from a file. */
+ DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
+ file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
+ BufFileReadExact(file, &snap_size, sizeof(snap_size));
+ snap_space = (char *) palloc(snap_size);
+ BufFileReadExact(file, snap_space, snap_size);
+ BufFileClose(file);
+
+ SpinLockAcquire(&shared->mutex);
+ shared->sfs_valid = false;
+ SpinLockRelease(&shared->mutex);
+
+ /* Restore it. */
+ snapshot = RestoreSnapshot(snap_space);
+ pfree(snap_space);
+
+ return snapshot;
+}
+
+bool
+IsRepackWorker(void)
+{
+ return is_repack_worker;
+}
+
+/*
+ * Handle receipt of an interrupt indicating a repack worker message.
+ *
+ * Note: this is called within a signal handler! All we can do is set
+ * a flag that will cause the next CHECK_FOR_INTERRUPTS() to invoke
+ * ProcessRepackMessages().
+ */
+void
+HandleRepackMessageInterrupt(void)
+{
+ InterruptPending = true;
+ RepackMessagePending = true;
+ SetLatch(MyLatch);
+}
+
+/*
+ * Process any queued protocol messages received from parallel workers.
+ */
+void
+ProcessRepackMessages(void)
+{
+ MemoryContext oldcontext;
+
+ static MemoryContext hpm_context = NULL;
+
+ /*
+ * Nothing to do if we haven't launched the worker yet or have already
+ * terminated it.
+ */
+ if (decoding_worker == NULL)
+ return;
+
+ /*
+ * This is invoked from ProcessInterrupts(), and since some of the
+ * functions it calls contain CHECK_FOR_INTERRUPTS(), there is a potential
+ * for recursive calls if more signals are received while this runs. It's
+ * unclear that recursive entry would be safe, and it doesn't seem useful
+ * even if it is safe, so let's block interrupts until done.
+ */
+ HOLD_INTERRUPTS();
+
+ /*
+ * Moreover, CurrentMemoryContext might be pointing almost anywhere. We
+ * don't want to risk leaking data into long-lived contexts, so let's do
+ * our work here in a private context that we can reset on each use.
+ */
+ if (hpm_context == NULL) /* first time through? */
+ hpm_context = AllocSetContextCreate(TopMemoryContext,
+ "ProcessParallelMessages",
+ ALLOCSET_DEFAULT_SIZES);
+ else
+ MemoryContextReset(hpm_context);
+
+ oldcontext = MemoryContextSwitchTo(hpm_context);
+
+ /* OK to process messages. Reset the flag saying there are more to do. */
+ RepackMessagePending = false;
+
+ /*
+ * Read as many messages as we can from each worker, but stop when no more
+ * messages can be read from the worker without blocking.
+ */
+ while (true)
+ {
+ shm_mq_result res;
+ Size nbytes;
+ void *data;
+
+ res = shm_mq_receive(decoding_worker->error_mqh, &nbytes,
+ &data, true);
+ if (res == SHM_MQ_WOULD_BLOCK)
+ break;
+ else if (res == SHM_MQ_SUCCESS)
+ {
+ StringInfoData msg;
+
+ initStringInfo(&msg);
+ appendBinaryStringInfo(&msg, data, nbytes);
+ ProcessRepackMessage(&msg);
+ pfree(msg.data);
+ }
+ else
+ {
+ /*
+ * The decoding worker is special in that it exits as soon as it
+ * has its work done. Thus the DETACHED result code is fine.
+ */
+ Assert(res = SHM_MQ_DETACHED);
+
+ break;
+ }
+ }
+
+ MemoryContextSwitchTo(oldcontext);
+
+ /* Might as well clear the context on our way out */
+ MemoryContextReset(hpm_context);
+
+ RESUME_INTERRUPTS();
+}
+
+/*
+ * Process a single protocol message received from a single parallel worker.
+ */
+static void
+ProcessRepackMessage(StringInfo msg)
+{
+ char msgtype;
+
+ msgtype = pq_getmsgbyte(msg);
+
+ switch (msgtype)
+ {
+ case PqMsg_ErrorResponse:
+ case PqMsg_NoticeResponse:
+ {
+ ErrorData edata;
+
+ /* Parse ErrorResponse or NoticeResponse. */
+ pq_parse_errornotice(msg, &edata);
+
+ /* Death of a worker isn't enough justification for suicide. */
+ edata.elevel = Min(edata.elevel, ERROR);
+
+ /*
+ * If desired, add a context line to show that this is a
+ * message propagated from a parallel worker. Otherwise, it
+ * can sometimes be confusing to understand what actually
+ * happened.
+ */
+ if (edata.context)
+ edata.context = psprintf("%s\n%s", edata.context,
+ _("decoding worker"));
+ else
+ edata.context = pstrdup(_("decoding worker"));
+
+ /* Rethrow error or print notice. */
+ ThrowErrorData(&edata);
+
+ break;
+ }
+
+ default:
+ {
+ elog(ERROR, "unrecognized message type received from decoding worker: %c (message length %d bytes)",
+ msgtype, msg->len);
+ }
+ }
+}
diff --git a/src/backend/libpq/pqmq.c b/src/backend/libpq/pqmq.c
index 2b75de0ddef..28a5a400fb1 100644
--- a/src/backend/libpq/pqmq.c
+++ b/src/backend/libpq/pqmq.c
@@ -14,6 +14,7 @@
#include "postgres.h"
#include "access/parallel.h"
+#include "commands/cluster.h"
#include "libpq/libpq.h"
#include "libpq/pqformat.h"
#include "libpq/pqmq.h"
@@ -175,6 +176,10 @@ mq_putmessage(char msgtype, const char *s, size_t len)
SendProcSignal(pq_mq_parallel_leader_pid,
PROCSIG_PARALLEL_APPLY_MESSAGE,
pq_mq_parallel_leader_proc_number);
+ else if (IsRepackWorker())
+ SendProcSignal(pq_mq_parallel_leader_pid,
+ PROCSIG_REPACK_MESSAGE,
+ pq_mq_parallel_leader_proc_number);
else
{
Assert(IsParallelWorker());
diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c
index 8e1068969ae..2d1ba94a45f 100644
--- a/src/backend/postmaster/bgworker.c
+++ b/src/backend/postmaster/bgworker.c
@@ -13,6 +13,7 @@
#include "postgres.h"
#include "access/parallel.h"
+#include "commands/cluster.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "pgstat.h"
@@ -135,6 +136,9 @@ static const struct
},
{
"SequenceSyncWorkerMain", SequenceSyncWorkerMain
+ },
+ {
+ "RepackWorkerMain", RepackWorkerMain
}
};
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index 1b11ed63dc6..b3fd7fec392 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -205,7 +205,11 @@ StartupDecodingContext(List *output_plugin_options,
ctx->slot = slot;
- ctx->reader = XLogReaderAllocate(wal_segment_size, NULL, xl_routine, ctx);
+ /*
+ * TODO A separate patch for PG core, unless there's really a reason to
+ * pass ctx for private_data (May extensions expect ctx?).
+ */
+ ctx->reader = XLogReaderAllocate(wal_segment_size, NULL, xl_routine, NULL);
if (!ctx->reader)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index c8930640a0d..fb9956d392d 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -168,17 +168,13 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
HeapTuple tuple)
{
RepackDecodingState *dstate;
- char *change_raw;
- ConcurrentChange change;
+ char kind_byte = (char) kind;
bool flattened = false;
- Size size;
- Datum values[1];
- bool isnull[1];
- char *dst;
dstate = (RepackDecodingState *) ctx->output_writer_private;
- size = VARHDRSZ + SizeOfConcurrentChange;
+ /* Store the change kind. */
+ BufFileWrite(dstate->file, &kind_byte, 1);
/*
* ReorderBufferCommit() stores the TOAST chunks in its private memory
@@ -195,46 +191,12 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
tuple = toast_flatten_tuple(tuple, dstate->tupdesc);
flattened = true;
}
+ /* Store the tuple size ... */
+ BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len));
+ /* ... and the tuple itself. */
+ BufFileWrite(dstate->file, tuple->t_data, tuple->t_len);
- size += tuple->t_len;
- if (size >= MaxAllocSize)
- elog(ERROR, "Change is too big.");
-
- /* Construct the change. */
- change_raw = (char *) palloc0(size);
- SET_VARSIZE(change_raw, size);
-
- /*
- * Since the varlena alignment might not be sufficient for the structure,
- * set the fields in a local instance and remember where it should
- * eventually be copied.
- */
- change.kind = kind;
- dst = (char *) VARDATA(change_raw);
-
- /*
- * Copy the tuple.
- *
- * Note: change->tup_data.t_data must be fixed on retrieval!
- */
- memcpy(&change.tup_data, tuple, sizeof(HeapTupleData));
- memcpy(dst, &change, SizeOfConcurrentChange);
- dst += SizeOfConcurrentChange;
- memcpy(dst, tuple->t_data, tuple->t_len);
-
- /* The data has been copied. */
+ /* Free the flat copy if created above. */
if (flattened)
pfree(tuple);
-
- /* Store as tuple of 1 bytea column. */
- values[0] = PointerGetDatum(change_raw);
- isnull[0] = false;
- tuplestore_putvalues(dstate->tstore, dstate->tupdesc_change,
- values, isnull);
-
- /* Accounting. */
- dstate->nchanges++;
-
- /* Cleanup. */
- pfree(change_raw);
}
diff --git a/src/backend/storage/ipc/procsignal.c b/src/backend/storage/ipc/procsignal.c
index 087821311cc..af12144795b 100644
--- a/src/backend/storage/ipc/procsignal.c
+++ b/src/backend/storage/ipc/procsignal.c
@@ -19,6 +19,7 @@
#include "access/parallel.h"
#include "commands/async.h"
+#include "commands/cluster.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "port/pg_bitutils.h"
@@ -694,6 +695,9 @@ procsignal_sigusr1_handler(SIGNAL_ARGS)
if (CheckProcSignal(PROCSIG_PARALLEL_APPLY_MESSAGE))
HandleParallelApplyMessageInterrupt();
+ if (CheckProcSignal(PROCSIG_REPACK_MESSAGE))
+ HandleRepackMessageInterrupt();
+
if (CheckProcSignal(PROCSIG_RECOVERY_CONFLICT_DATABASE))
HandleRecoveryConflictInterrupt(PROCSIG_RECOVERY_CONFLICT_DATABASE);
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 7dd75a490aa..4a4858882f0 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -36,6 +36,7 @@
#include "access/xact.h"
#include "catalog/pg_type.h"
#include "commands/async.h"
+#include "commands/cluster.h"
#include "commands/event_trigger.h"
#include "commands/explain_state.h"
#include "commands/prepare.h"
@@ -3541,6 +3542,9 @@ ProcessInterrupts(void)
if (ParallelApplyMessagePending)
ProcessParallelApplyMessages();
+
+ if (RepackMessagePending)
+ ProcessRepackMessages();
}
/*
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index f39830dbb34..cbcc8550960 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -62,6 +62,7 @@ LOGICAL_APPLY_MAIN "Waiting in main loop of logical replication apply process."
LOGICAL_LAUNCHER_MAIN "Waiting in main loop of logical replication launcher process."
LOGICAL_PARALLEL_APPLY_MAIN "Waiting in main loop of logical replication parallel apply process."
RECOVERY_WAL_STREAM "Waiting in main loop of startup process for WAL to arrive, during streaming recovery."
+REPACK_WORKER_MAIN "Waiting in main loop of REPACK decoding worker process."
REPLICATION_SLOTSYNC_MAIN "Waiting in main loop of slot sync worker."
REPLICATION_SLOTSYNC_SHUTDOWN "Waiting for slot sync worker to shut down."
SYSLOGGER_MAIN "Waiting in main loop of syslogger process."
@@ -153,6 +154,7 @@ RECOVERY_CONFLICT_SNAPSHOT "Waiting for recovery conflict resolution for a vacuu
RECOVERY_CONFLICT_TABLESPACE "Waiting for recovery conflict resolution for dropping a tablespace."
RECOVERY_END_COMMAND "Waiting for <xref linkend="guc-recovery-end-command"/> to complete."
RECOVERY_PAUSE "Waiting for recovery to be resumed."
+REPACK_WORKER_EXPORT "Waiting for decoding worker to export a new output file."
REPLICATION_ORIGIN_DROP "Waiting for a replication origin to become inactive so it can be dropped."
REPLICATION_SLOT_DROP "Waiting for a replication slot to become inactive so it can be dropped."
RESTORE_COMMAND "Waiting for <xref linkend="guc-restore-command"/> to complete."
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index d8f76d325f9..321c00682ec 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -22,7 +22,6 @@
#include "access/xact.h"
#include "commands/vacuum.h"
#include "executor/tuptable.h"
-#include "replication/logical.h"
#include "storage/read_stream.h"
#include "utils/rel.h"
#include "utils/snapshot.h"
@@ -631,7 +630,6 @@ typedef struct TableAmRoutine
bool use_sort,
TransactionId OldestXmin,
Snapshot snapshot,
- LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1651,8 +1649,6 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator)
* - *multi_cutoff - ditto
* - snapshot - if != NULL, ignore data changes done by transactions that this
* (MVCC) snapshot considers still in-progress or in the future.
- * - decoding_ctx - logical decoding context, to capture concurrent data
- * changes.
*
* Output parameters:
* - *xid_cutoff - rel's new relfrozenxid value, may be invalid
@@ -1666,7 +1662,6 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
bool use_sort,
TransactionId OldestXmin,
Snapshot snapshot,
- LogicalDecodingContext *decoding_ctx,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
@@ -1675,7 +1670,7 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
{
OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex,
use_sort, OldestXmin,
- snapshot, decoding_ctx,
+ snapshot,
xid_cutoff, multi_cutoff,
num_tuples, tups_vacuumed,
tups_recently_dead);
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index b43a1740053..0ac70ec30d7 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -17,6 +17,7 @@
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
#include "replication/logical.h"
+#include "storage/buffile.h"
#include "storage/lock.h"
#include "storage/relfilelocator.h"
#include "utils/relcache.h"
@@ -47,6 +48,9 @@ typedef struct ClusterParams
extern RelFileLocator repacked_rel_locator;
extern RelFileLocator repacked_rel_toast_locator;
+/*
+ * Stored as a single byte in the output file.
+ */
typedef enum
{
CHANGE_INSERT,
@@ -55,68 +59,30 @@ typedef enum
CHANGE_DELETE
} ConcurrentChangeKind;
-typedef struct ConcurrentChange
-{
- /* See the enum above. */
- ConcurrentChangeKind kind;
-
- /*
- * The actual tuple.
- *
- * The tuple data follows the ConcurrentChange structure. Before use make
- * sure the tuple is correctly aligned (ConcurrentChange can be stored as
- * bytea) and that tuple->t_data is fixed.
- */
- HeapTupleData tup_data;
-} ConcurrentChange;
-
-#define SizeOfConcurrentChange (offsetof(ConcurrentChange, tup_data) + \
- sizeof(HeapTupleData))
-
/*
* Logical decoding state.
*
- * Here we store the data changes that we decode from WAL while the table
- * contents is being copied to a new storage. Also the necessary metadata
- * needed to apply these changes to the table is stored here.
+ * The output plugin uses it to store the data changes that it decodes from
+ * WAL while the table contents is being copied to a new storage.
*/
typedef struct RepackDecodingState
{
/* The relation whose changes we're decoding. */
Oid relid;
- /* Replication slot name. */
- NameData slotname;
-
- /*
- * Decoded changes are stored here. Although we try to avoid excessive
- * batches, it can happen that the changes need to be stored to disk. The
- * tuplestore does this transparently.
- */
- Tuplestorestate *tstore;
-
- /* The current number of changes in tstore. */
- double nchanges;
-
- /*
- * Descriptor to store the ConcurrentChange structure serialized (bytea).
- * We can't store the tuple directly because tuplestore only supports
- * minimum tuple and we may need to transfer OID system column from the
- * output plugin. Also we need to transfer the change kind, so it's better
- * to put everything in the structure than to use 2 tuplestores "in
- * parallel".
- */
- TupleDesc tupdesc_change;
-
- /* Tuple descriptor needed to update indexes. */
+ /* Tuple descriptor of the relation being processed. */
TupleDesc tupdesc;
- /* Slot to retrieve data from tstore. */
- TupleTableSlot *tsslot;
-
- ResourceOwner resowner;
+ /* The current output file. */
+ BufFile *file;
} RepackDecodingState;
+extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
+
+extern bool IsRepackWorker(void);
+extern void HandleRepackMessageInterrupt(void);
+extern void ProcessRepackMessages(void);
+
extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid indexOid,
@@ -125,9 +91,6 @@ extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid,
LOCKMODE lockmode);
extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_internal);
-extern void repack_decode_concurrent_changes(LogicalDecodingContext *ctx,
- XLogRecPtr end_of_wal);
-
extern Oid make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
char relpersistence, LOCKMODE lockmode);
extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
@@ -140,4 +103,5 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
MultiXactId cutoffMulti,
char newrelpersistence);
+extern void RepackWorkerMain(Datum main_arg);
#endif /* CLUSTER_H */
diff --git a/src/include/storage/procsignal.h b/src/include/storage/procsignal.h
index afeeb1ca019..c0a66516b66 100644
--- a/src/include/storage/procsignal.h
+++ b/src/include/storage/procsignal.h
@@ -36,6 +36,7 @@ typedef enum
PROCSIG_BARRIER, /* global barrier interrupt */
PROCSIG_LOG_MEMORY_CONTEXT, /* ask backend to log the memory contexts */
PROCSIG_PARALLEL_APPLY_MESSAGE, /* Message from parallel apply workers */
+ PROCSIG_REPACK_MESSAGE, /* Message from repack worker */
/* Recovery conflict reasons */
PROCSIG_RECOVERY_CONFLICT_FIRST,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 3139b14e85f..35344910f65 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -488,7 +488,6 @@ CompressFileHandle
CompressionLocation
CompressorState
ComputeXidHorizonsResult
-ConcurrentChange
ConcurrentChangeKind
ConditionVariable
ConditionVariableMinimallyPadded
@@ -629,6 +628,9 @@ DeclareCursorStmt
DecodedBkpBlock
DecodedXLogRecord
DecodingOutputState
+DecodingWorker
+DecodingWorkerShared
+DecodingWorkerState
DefElem
DefElemAction
DefaultACLInfo
--
2.47.3
[text/plain] v28-0006-Use-multiple-snapshots-to-copy-the-data.patch (64.8K, ../210036.1765651719@localhost/7-v28-0006-Use-multiple-snapshots-to-copy-the-data.patch)
download | inline diff:
From 32accb96480ddf42847ae23f30f23636d64eeb50 Mon Sep 17 00:00:00 2001
From: Antonin Houska <ah@cybertec.at>
Date: Sat, 13 Dec 2025 19:27:18 +0100
Subject: [PATCH 6/6] Use multiple snapshots to copy the data.
REPACK (CONCURRENTLY) does not prevent applications from using the table that
is being processed, however it can prevent the xmin horizon from advancing and
thus restrict VACUUM for the whole database. This patch adds the ability to
use particular snapshot only for certain range of pages. Each time that number
of pages is processed, a new snapshot is built, which supposedly has its xmin
higher than the previous snapshot.
The data copying works as follows:
1. Have the logical decoding system build a snapshot S0 for range R0 at
LSN0. This snapshot sees all the data changes whose commit records have
LSN < LSN0.
2. Copy the pages in that range to the new relation. The changes not visible
to the snapshot (because their transactions are still running) will
appear in the output of the logical decoding system as soon as their
commit records appear in WAL.
3. Perform logical decoding of all changes we find in WAL for the table
we're repacking, put them aside and remember that out of these we can
only apply those that affect the range R0 in the old
relation. (Naturally, we cannot apply ones that belong to other pages
because it's impossible to UPDATE / DELETE a row in the new relation if
it hasn't been copied yet.) Once the decoding is done, consider LSN1 to
be the position of the end of the last WAL record decoded.
4. Build a new snapshot S1 at position LSN1, i.e. one that sees all the data
whose commit records are at WAL positions < LSN1. Use this snapshot to
copy the range of pages R1.
5. Perform logical decoding like in step 3, but remember, that out of this
next set, only changes belonging to ranges R0 *and* R1 in the old table
can be applied.
6. etc
Note that the changes decoded above should not be applied to the new relation
until the whole relation has been copied. The point is that we need "identity
index" to apply UPDATE and DELETE statements, and bulk creation of indexes on
the already copied heap is probably better than retail insertions during the
copying.
Special attention needs to be paid to UPDATES that span page ranges. For
example, if the old tuple is in range R0, but the new tuple is in R1, and R1
hasn't been copied yet, we only DELETE the old version from the new
relation. The new version will be handled during processing of range R1. The
snapshot S1 will be based on WAL position following that UPDATE, so it'll see
the new tuple if its transaction's commit record is at WAL position lower than
the position where we built the snapshot. On the other hand, if the commit
record appears at higher position than the that of the snapshot, the
corresponding INSERT will be decoded and replayed sometime later: once the
scan of R1 started, changes of tuples belonging to it are no longer filtered
out.
Likewise, if the old tuple is in range R1 (not yet copied) but the new tuple
is in R0, we only perform INSERT on the new relation. The deletion of the old
version will either be visible to the snapshot S1 (i.e. the snapshot won't see
the old version), or replayed later.
This approach introduces one limitation though: if the USING INDEX clause is
specified, an explicit sort is always used. Index scan wouldn't work because
it does not return the tuples sorted by CTID. That way we wouldn't be able to
split the copying into ranges of pages. I'm not sure it's serious. If REPACK
runs concurrently and does not restrict VACUUM, the execution time should not
be critical.
A new GUC repack_snapshot_after can be used to set the number of pages per
snapshot. It's currently classified as DEVELOPER_OPTIONS and may be replaced
by a constant after enough evaluation is done.
---
src/backend/access/heap/heapam_handler.c | 144 ++++-
src/backend/commands/cluster.c | 561 +++++++++++++-----
src/backend/replication/logical/decode.c | 47 +-
src/backend/replication/logical/logical.c | 30 +-
.../replication/logical/reorderbuffer.c | 50 ++
src/backend/replication/logical/snapbuild.c | 27 +-
.../pgoutput_repack/pgoutput_repack.c | 2 +
src/backend/utils/misc/guc_parameters.dat | 10 +
src/backend/utils/misc/guc_tables.c | 1 +
src/include/access/tableam.h | 14 +-
src/include/commands/cluster.h | 65 ++
src/include/replication/logical.h | 2 +-
src/include/replication/reorderbuffer.h | 1 +
src/include/replication/snapbuild.h | 2 +-
src/tools/pgindent/typedefs.list | 3 +-
15 files changed, 771 insertions(+), 188 deletions(-)
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index cb09e6fd1dc..b87fad605e4 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -33,6 +33,7 @@
#include "catalog/index.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
+#include "commands/cluster.h"
#include "commands/progress.h"
#include "executor/executor.h"
#include "miscadmin.h"
@@ -686,12 +687,12 @@ static void
heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
Relation OldIndex, bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead)
+ double *tups_recently_dead,
+ void *tableam_data)
{
RewriteState rwstate = NULL;
IndexScanDesc indexScan;
@@ -707,7 +708,10 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
bool *isnull;
BufferHeapTupleTableSlot *hslot;
BlockNumber prev_cblock = InvalidBlockNumber;
- bool concurrent = snapshot != NULL;
+ ConcurrentChangeContext *ctx = (ConcurrentChangeContext *) tableam_data;
+ bool concurrent = ctx != NULL;
+ Snapshot snapshot = NULL;
+ BlockNumber range_end = InvalidBlockNumber;
/* Remember if it's a system catalog */
is_system_catalog = IsSystemRelation(OldHeap);
@@ -744,8 +748,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
* that still need to be copied, we scan with SnapshotAny and use
* HeapTupleSatisfiesVacuum for the visibility test.
*
- * In the CONCURRENTLY case, we do regular MVCC visibility tests, using
- * the snapshot passed by the caller.
+ * In the CONCURRENTLY case, we do regular MVCC visibility tests. The
+ * snapshot changes several times during the scan so that we do not block
+ * the progress of the xmin horizon for VACUUM too much.
*/
if (OldIndex != NULL && !use_sort)
{
@@ -773,10 +778,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP);
- tableScan = table_beginscan(OldHeap,
- snapshot ? snapshot : SnapshotAny,
- 0, (ScanKey) NULL);
+ tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL);
heapScan = (HeapScanDesc) tableScan;
+
+ /*
+ * In CONCURRENTLY mode we scan the table by ranges of blocks and the
+ * algorithm below expects forward direction. (No other direction
+ * should be set here regardless concurrently anyway.)
+ */
+ Assert(heapScan->rs_dir == ForwardScanDirection || !concurrent);
indexScan = NULL;
/* Set total heap blocks */
@@ -787,6 +797,24 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
slot = table_slot_create(OldHeap, NULL);
hslot = (BufferHeapTupleTableSlot *) slot;
+ if (concurrent)
+ {
+ /*
+ * Do not block the progress of xmin horizons.
+ *
+ * TODO Analyze thoroughly if this might have bad consequences.
+ */
+ PopActiveSnapshot();
+ InvalidateCatalogSnapshot();
+
+ /*
+ * Wait until the worker has the initial snapshot and retrieve it.
+ */
+ snapshot = repack_get_snapshot(ctx);
+
+ PushActiveSnapshot(snapshot);
+ }
+
/*
* Scan through the OldHeap, either in OldIndex order or sequentially;
* copy each tuple into the NewHeap, or transiently to the tuplesort
@@ -803,6 +831,13 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
if (indexScan != NULL)
{
+ /*
+ * Index scan should not be used in the CONCURRENTLY case because
+ * it returns tuples in random order, so we could not split the
+ * scan into a series of page ranges.
+ */
+ Assert(!concurrent);
+
if (!index_getnext_slot(indexScan, ForwardScanDirection, slot))
break;
@@ -824,6 +859,18 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
*/
pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED,
heapScan->rs_nblocks);
+
+ if (concurrent)
+ {
+ PopActiveSnapshot();
+
+ /*
+ * For the last range, there are no restriction on block
+ * numbers, so the concurrent data changes pertaining to
+ * this range can decoded (and applied) anytime after this
+ * loop.
+ */
+ }
break;
}
@@ -922,6 +969,75 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
continue;
}
}
+ else
+ {
+ BlockNumber blkno;
+ bool visible;
+
+ /*
+ * With CONCURRENTLY, we use each snapshot only for certain range
+ * of pages, so that VACUUM does not get block for too long. So
+ * first check if the tuple falls into the current range.
+ */
+ blkno = BufferGetBlockNumber(buf);
+
+ /* The first block of the scan? */
+ if (!BlockNumberIsValid(ctx->first_block))
+ {
+ Assert(!BlockNumberIsValid(range_end));
+
+ ctx->first_block = blkno;
+ range_end = repack_blocks_per_snapshot;
+ }
+ else
+ {
+ Assert(BlockNumberIsValid(range_end));
+
+ /* End of the current range? */
+ if (blkno >= range_end)
+ {
+ XLogRecPtr end_of_wal;
+
+ PopActiveSnapshot();
+
+ /*
+ * XXX It might be worth Assert(CatalogSnapshot == NULL)
+ * here, however that symbol is not external.
+ */
+
+ /*
+ * Decode all the concurrent data changes committed so far
+ * - these will be applicable to the current range.
+ */
+ end_of_wal = GetFlushRecPtr(NULL);
+ repack_get_concurrent_changes(ctx, end_of_wal, range_end,
+ true, false);
+
+ /*
+ * Define the next range.
+ */
+ range_end = blkno + repack_blocks_per_snapshot;
+
+ /*
+ * Get the snapshot for the next range - it should have
+ * been built at the position right after the last change
+ * decoded. Data present in the next range of blocks will
+ * either be visible to the snapshot or appear in the next
+ * batch of decoded changes.
+ */
+ snapshot = repack_get_snapshot(ctx);
+ PushActiveSnapshot(snapshot);
+ }
+ }
+
+ /* Finally check the tuple visibility. */
+ LockBuffer(buf, BUFFER_LOCK_SHARE);
+ visible = HeapTupleSatisfiesVisibility(tuple, snapshot, buf);
+ LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+
+ if (!visible)
+ continue;
+ }
*num_tuples += 1;
if (tuplesort != NULL)
@@ -956,6 +1072,18 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
}
}
+ if (concurrent)
+ {
+ XLogRecPtr end_of_wal;
+
+ /* Decode the changes belonging to the last range. */
+ end_of_wal = GetFlushRecPtr(NULL);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber,
+ false, false);
+
+ PushActiveSnapshot(GetTransactionSnapshot());
+ }
+
if (indexScan != NULL)
index_endscan(indexScan);
if (tableScan != NULL)
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index b0383c1375f..3eb642b996d 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -110,38 +110,27 @@ typedef struct
RelFileLocator repacked_rel_locator = {.relNumber = InvalidOid};
RelFileLocator repacked_rel_toast_locator = {.relNumber = InvalidOid};
-/*
- * Everything we need to call ExecInsertIndexTuples().
- */
-typedef struct IndexInsertState
-{
- ResultRelInfo *rri;
- EState *estate;
-} IndexInsertState;
-
/* The WAL segment being decoded. */
static XLogSegNo repack_current_segment = 0;
/*
- * Information needed to apply concurrent data changes.
+ * When REPACK (CONCURRENTLY) copies data to the new heap, a new snapshot is
+ * built after processing this many pages.
*/
-typedef struct ChangeDest
-{
- /* The relation the changes are applied to. */
- Relation rel;
+int repack_blocks_per_snapshot = 1024;
- /*
- * The following is needed to find the existing tuple if the change is
- * UPDATE or DELETE. 'ident_key' should have all the fields except for
- * 'sk_argument' initialized.
- */
- Relation ident_index;
- ScanKey ident_key;
- int ident_key_nentries;
+/*
+ * Remember here to which pages should applied to changes recorded in given
+ * file.
+ */
+typedef struct RepackApplyRange
+{
+ /* The first block of the next range. */
+ BlockNumber end;
- /* Needed to update indexes of rel_dst. */
- IndexInsertState *iistate;
-} ChangeDest;
+ /* File containing the changes to be applied to blocks in this range. */
+ char *fname;
+} RepackApplyRange;
/*
* Layout of shared memory used for communication between backend and the
@@ -152,6 +141,9 @@ typedef struct DecodingWorkerShared
/* Is the decoding initialized? */
bool initialized;
+ /* Set to request a snapshot. */
+ bool snapshot_requested;
+
/*
* Once the worker has reached this LSN, it should close the current
* output file and either create a new one or exit, according to the field
@@ -159,20 +151,25 @@ typedef struct DecodingWorkerShared
* the WAL available and keep checking this field. It is ok if the worker
* had already decoded records whose LSN is >= lsn_upto before this field
* has been set.
+ *
+ * Set a valid LSN to request data changes.
*/
XLogRecPtr lsn_upto;
+#define WORKER_RESPONSE_SNAPSHOT 0x1
+#define WORKER_RESPONSE_CHANGES 0x2
+ /* Which kind of data is ready? */
+ int response;;
+
/* Exit after closing the current file? */
bool done;
/* The output is stored here. */
SharedFileSet sfs;
- /* Can backend read the file contents? */
- bool sfs_valid;
-
/* Number of the last file exported by the worker. */
- int last_exported;
+ int last_exported_changes;
+ int last_exported_snapshot;
/* Synchronize access to the fields above. */
slock_t mutex;
@@ -214,26 +211,14 @@ typedef struct DecodingWorkerShared
* the fileset name.)
*/
static inline void
-DecodingWorkerFileName(char *fname, Oid relid, uint32 seq)
+DecodingWorkerFileName(char *fname, Oid relid, uint32 seq, bool snapshot)
{
- snprintf(fname, MAXPGPATH, "%u-%u", relid, seq);
+ if (!snapshot)
+ snprintf(fname, MAXPGPATH, "%u-%u", relid, seq);
+ else
+ snprintf(fname, MAXPGPATH, "%u-%u-snapshot", relid, seq);
}
-/*
- * Backend-local information to control the decoding worker.
- */
-typedef struct DecodingWorker
-{
- /* The worker. */
- BackgroundWorkerHandle *handle;
-
- /* DecodingWorkerShared is in this segment. */
- dsm_segment *seg;
-
- /* Handle of the error queue. */
- shm_mq_handle *error_mqh;
-} DecodingWorker;
-
/* Pointer to currently running decoding worker. */
static DecodingWorker *decoding_worker = NULL;
@@ -250,11 +235,11 @@ static void check_repack_concurrently_requirements(Relation rel);
static void rebuild_relation(Relation OldHeap, Relation index, bool verbose,
bool concurrent);
static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot,
bool verbose,
bool *pSwapToastByContent,
TransactionId *pFreezeXid,
- MultiXactId *pCutoffMulti);
+ MultiXactId *pCutoffMulti,
+ ConcurrentChangeContext *ctx);
static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
MemoryContext permcxt);
static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -264,9 +249,12 @@ static bool cluster_is_permitted_for_relation(RepackCommand cmd,
Oid relid, Oid userid);
static LogicalDecodingContext *setup_logical_decoding(Oid relid);
-static bool decode_concurrent_changes(LogicalDecodingContext *ctx,
+static bool decode_concurrent_changes(LogicalDecodingContext *decoding_ctx,
DecodingWorkerShared *shared);
-static void apply_concurrent_changes(BufFile *file, ChangeDest *dest);
+static void apply_concurrent_changes(ConcurrentChangeContext *ctx);
+static void apply_concurrent_changes_file(ConcurrentChangeContext *ctx,
+ BufFile *file,
+ BlockNumber range_end);
static void apply_concurrent_insert(Relation rel, HeapTuple tup,
IndexInsertState *iistate,
TupleTableSlot *index_slot);
@@ -275,12 +263,14 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup,
IndexInsertState *iistate,
TupleTableSlot *index_slot);
static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
-static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
+static bool is_tuple_in_block_range(HeapTuple tup, BlockNumber start,
+ BlockNumber end);
+static HeapTuple find_target_tuple(Relation rel,
+ ConcurrentChangeContext *ctx,
HeapTuple tup_key,
TupleTableSlot *ident_slot);
-static void process_concurrent_changes(XLogRecPtr end_of_wal,
- ChangeDest *dest,
- bool done);
+static void repack_add_block_range(ConcurrentChangeContext *ctx,
+ BlockNumber end, char *fname);
static IndexInsertState *get_index_insert_state(Relation relation,
Oid ident_index_id,
Relation *ident_index_p);
@@ -291,7 +281,8 @@ static void cleanup_logical_decoding(LogicalDecodingContext *ctx);
static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
TransactionId frozenXid,
- MultiXactId cutoffMulti);
+ MultiXactId cutoffMulti,
+ ConcurrentChangeContext *ctx);
static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes);
static Relation process_single_relation(RepackStmt *stmt,
LOCKMODE lockmode,
@@ -302,9 +293,8 @@ static Oid determine_clustered_index(Relation rel, bool usingindex,
static void start_decoding_worker(Oid relid);
static void stop_decoding_worker(void);
static void repack_worker_internal(dsm_segment *seg);
-static void export_initial_snapshot(Snapshot snapshot,
- DecodingWorkerShared *shared);
-static Snapshot get_initial_snapshot(DecodingWorker *worker);
+static void export_snapshot(Snapshot snapshot,
+ DecodingWorkerShared *shared);
static void ProcessRepackMessage(StringInfo msg);
static const char *RepackCommandAsString(RepackCommand cmd);
@@ -1008,6 +998,15 @@ check_repack_concurrently_requirements(Relation rel)
RelationGetRelationName(rel)),
(errhint("Relation \"%s\" has no identity index.",
RelationGetRelationName(rel)))));
+
+ /*
+ * In the CONCURRENTLY mode we don't want to use the same snapshot
+ * throughout the whole processing, as it could block the progress of xmin
+ * horizon.
+ */
+ if (IsolationUsesXactSnapshot())
+ ereport(ERROR,
+ (errmsg("REPACK (CONCURRENTLY) does not support transaction isolation higher than READ COMMITTED")));
}
@@ -1038,7 +1037,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
bool swap_toast_by_content;
TransactionId frozenXid;
MultiXactId cutoffMulti;
- Snapshot snapshot = NULL;
+ ConcurrentChangeContext *ctx = NULL;
#if USE_ASSERT_CHECKING
LOCKMODE lmode;
@@ -1050,6 +1049,13 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
if (concurrent)
{
+ /*
+ * This is only needed here to gather the data changes and range
+ * information during the copying. The fields needed to apply the
+ * changes be filled later.
+ */
+ ctx = palloc0_object(ConcurrentChangeContext);
+
/*
* The worker needs to be member of the locking group we're the leader
* of. We ought to become the leader before the worker starts. The
@@ -1075,13 +1081,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
* REPACK CONCURRENTLY.
*/
start_decoding_worker(tableOid);
-
- /*
- * Wait until the worker has the initial snapshot and retrieve it.
- */
- snapshot = get_initial_snapshot(decoding_worker);
-
- PushActiveSnapshot(snapshot);
+ ctx->worker = decoding_worker;
}
/* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */
@@ -1105,21 +1105,25 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent
NewHeap = table_open(OIDNewHeap, NoLock);
/* Copy the heap data into the new table in the desired order */
- copy_table_data(NewHeap, OldHeap, index, snapshot, verbose,
- &swap_toast_by_content, &frozenXid, &cutoffMulti);
-
- /* The historic snapshot won't be needed anymore. */
- if (snapshot)
+ if (concurrent)
{
- PopActiveSnapshot();
- UpdateActiveSnapshotCommandId();
+ ctx->first_block = InvalidBlockNumber;
+ ctx->block_ranges = NIL;
}
+ copy_table_data(NewHeap, OldHeap, index, verbose, &swap_toast_by_content,
+ &frozenXid, &cutoffMulti, ctx);
if (concurrent)
{
+ /*
+ * Make sure the active snapshot can see the data copied, so the rows
+ * can be updated / deleted.
+ */
+ UpdateActiveSnapshotCommandId();
+
Assert(!swap_toast_by_content);
rebuild_relation_finish_concurrent(NewHeap, OldHeap, index,
- frozenXid, cutoffMulti);
+ frozenXid, cutoffMulti, ctx);
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
@@ -1283,9 +1287,6 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
/*
* Do the physical copying of table data.
*
- * 'snapshot' and 'decoding_ctx': see table_relation_copy_for_cluster(). Pass
- * iff concurrent processing is required.
- *
* There are three output parameters:
* *pSwapToastByContent is set true if toast tables must be swapped by content.
* *pFreezeXid receives the TransactionId used as freeze cutoff point.
@@ -1293,8 +1294,9 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod,
*/
static void
copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
- Snapshot snapshot, bool verbose, bool *pSwapToastByContent,
- TransactionId *pFreezeXid, MultiXactId *pCutoffMulti)
+ bool verbose, bool *pSwapToastByContent,
+ TransactionId *pFreezeXid, MultiXactId *pCutoffMulti,
+ ConcurrentChangeContext *ctx)
{
Relation relRelation;
HeapTuple reltup;
@@ -1311,7 +1313,7 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
int elevel = verbose ? INFO : DEBUG2;
PGRUsage ru0;
char *nspname;
- bool concurrent = snapshot != NULL;
+ bool concurrent = ctx != NULL;
LOCKMODE lmode;
lmode = concurrent ? ShareUpdateExclusiveLock : AccessExclusiveLock;
@@ -1423,8 +1425,18 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
* provided, else plain seqscan.
*/
if (OldIndex != NULL && OldIndex->rd_rel->relam == BTREE_AM_OID)
- use_sort = plan_cluster_use_sort(RelationGetRelid(OldHeap),
- RelationGetRelid(OldIndex));
+ {
+ if (!concurrent)
+ use_sort = plan_cluster_use_sort(RelationGetRelid(OldHeap),
+ RelationGetRelid(OldIndex));
+ else
+
+ /*
+ * To use multiple snapshots, we need to process the table
+ * sequentially.
+ */
+ use_sort = true;
+ }
else
use_sort = false;
@@ -1453,11 +1465,11 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
* values (e.g. because the AM doesn't use freezing).
*/
table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort,
- cutoffs.OldestXmin, snapshot,
+ cutoffs.OldestXmin,
&cutoffs.FreezeLimit,
&cutoffs.MultiXactCutoff,
&num_tuples, &tups_vacuumed,
- &tups_recently_dead);
+ &tups_recently_dead, ctx);
/* return selected values to caller, get set as relfrozenxid/minmxid */
*pFreezeXid = cutoffs.FreezeLimit;
@@ -2610,6 +2622,7 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
DecodingWorkerShared *shared)
{
RepackDecodingState *dstate;
+ bool snapshot_requested;
XLogRecPtr lsn_upto;
bool done;
char fname[MAXPGPATH];
@@ -2617,11 +2630,14 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
dstate = (RepackDecodingState *) ctx->output_writer_private;
/* Open the output file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_changes + 1,
+ false);
dstate->file = BufFileCreateFileSet(&shared->sfs.fs, fname);
SpinLockAcquire(&shared->mutex);
lsn_upto = shared->lsn_upto;
+ snapshot_requested = shared->snapshot_requested;
done = shared->done;
SpinLockRelease(&shared->mutex);
@@ -2689,6 +2705,7 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
{
SpinLockAcquire(&shared->mutex);
lsn_upto = shared->lsn_upto;
+ snapshot_requested = shared->snapshot_requested;
/* 'done' should be set at the same time as 'lsn_upto' */
done = shared->done;
SpinLockRelease(&shared->mutex);
@@ -2710,28 +2727,108 @@ decode_concurrent_changes(LogicalDecodingContext *ctx,
*/
BufFileClose(dstate->file);
dstate->file = NULL;
+
+ /*
+ * Before publishing the data changes, export the snapshot too if
+ * requested. Publishing both at once makes sense because both are needed
+ * at the same time, and it's simpler.
+ */
+ if (snapshot_requested)
+ {
+ Snapshot snapshot;
+
+ snapshot = SnapBuildSnapshotForRepack(ctx->snapshot_builder);
+ export_snapshot(snapshot, shared);
+
+ /*
+ * Adjust the replication slot's xmin so that VACUUM can do more work.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, snapshot->xmin, false);
+ FreeSnapshot(snapshot);
+ }
+ else
+ {
+ /*
+ * If data changes were requested but no following snapshot, we don't
+ * care about xmin horizon because the heap copying should be done by
+ * now.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, InvalidTransactionId,
+ false);
+
+ }
+
+ /* Now announce that the output is available. */
SpinLockAcquire(&shared->mutex);
shared->lsn_upto = InvalidXLogRecPtr;
- shared->sfs_valid = true;
- shared->last_exported++;
+ shared->response |= WORKER_RESPONSE_CHANGES;
+ shared->last_exported_changes++;
+ if (snapshot_requested)
+ {
+ shared->snapshot_requested = false;
+ shared->response |= WORKER_RESPONSE_SNAPSHOT;
+ shared->last_exported_snapshot++;
+ }
SpinLockRelease(&shared->mutex);
+
ConditionVariableSignal(&shared->cv);
return done;
}
/*
- * Apply changes stored in 'file'.
+ * Apply all concurrent changes.
*/
static void
-apply_concurrent_changes(BufFile *file, ChangeDest *dest)
+apply_concurrent_changes(ConcurrentChangeContext *ctx)
+{
+ DecodingWorkerShared *shared;
+ ListCell *lc;
+
+ shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+ foreach(lc, ctx->block_ranges)
+ {
+ RepackApplyRange *range;
+ BufFile *file;
+
+ range = (RepackApplyRange *) lfirst(lc);
+
+ file = BufFileOpenFileSet(&shared->sfs.fs, range->fname, O_RDONLY,
+ false);
+
+ /*
+ * If range end is valid, the start should be as well.
+ */
+ Assert(!BlockNumberIsValid(range->end) ||
+ BlockNumberIsValid(ctx->first_block));
+
+ apply_concurrent_changes_file(ctx, file, range->end);
+ BufFileClose(file);
+
+ pfree(range->fname);
+ pfree(range);
+ }
+
+ /* Get ready for the next decoding. */
+ ctx->block_ranges = NIL;
+ ctx->first_block = InvalidBlockNumber;
+}
+
+/*
+ * Apply concurrent changes stored in 'file'.
+ */
+static void
+apply_concurrent_changes_file(ConcurrentChangeContext *ctx, BufFile *file,
+ BlockNumber range_end)
{
char kind;
uint32 t_len;
- Relation rel = dest->rel;
+ Relation rel = ctx->rel;
TupleTableSlot *index_slot,
*ident_slot;
HeapTuple tup_old = NULL;
+ bool check_range = BlockNumberIsValid(range_end);
/* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
index_slot = MakeSingleTupleTableSlot(RelationGetDescr(rel),
@@ -2759,8 +2856,8 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE);
BufFileReadExact(file, tup->t_data, t_len);
tup->t_len = t_len;
- ItemPointerSetInvalid(&tup->t_self);
- tup->t_tableOid = RelationGetRelid(dest->rel);
+ tup->t_tableOid = RelationGetRelid(ctx->rel);
+ BufFileReadExact(file, &tup->t_self, sizeof(tup->t_self));
if (kind == CHANGE_UPDATE_OLD)
{
@@ -2771,7 +2868,10 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
{
Assert(tup_old == NULL);
- apply_concurrent_insert(rel, tup, dest->iistate, index_slot);
+ if (!check_range ||
+ is_tuple_in_block_range(tup, ctx->first_block, range_end))
+ apply_concurrent_insert(rel, tup, ctx->iistate,
+ index_slot);
pfree(tup);
}
@@ -2792,16 +2892,52 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
/*
* Find the tuple to be updated or deleted.
*/
- tup_exist = find_target_tuple(rel, dest, tup_key, ident_slot);
- if (tup_exist == NULL)
- elog(ERROR, "failed to find target tuple");
+ if (!check_range ||
+ (is_tuple_in_block_range(tup_key, ctx->first_block,
+ range_end)))
+ {
+ /* The change needs to be applied to this tuple. */
+ tup_exist = find_target_tuple(rel, ctx, tup_key, ident_slot);
+ if (tup_exist == NULL)
+ elog(ERROR, "failed to find target tuple");
- if (kind == CHANGE_UPDATE_NEW)
- apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
- index_slot);
+ if (kind == CHANGE_DELETE)
+ apply_concurrent_delete(rel, tup_exist);
+ else
+ {
+ /* UPDATE */
+ if (!check_range || tup == tup_key ||
+ is_tuple_in_block_range(tup, ctx->first_block,
+ range_end))
+ /* The new tuple is in the same range. */
+ apply_concurrent_update(rel, tup, tup_exist,
+ ctx->iistate, index_slot);
+ else
+
+ /*
+ * The new key is in the other range, so only delete
+ * it from the current one. The new version should be
+ * visible to the snapshot that we'll use to copy the
+ * other block.
+ */
+ apply_concurrent_delete(rel, tup_exist);
+ }
+ }
else
- apply_concurrent_delete(rel, tup_exist);
-
+ {
+ /*
+ * The change belongs to another range, so we don't need to
+ * bother with the old tuple: the snapshot used for the other
+ * range won't see it, so it won't be copied. However, the new
+ * tuple still may need to go to the range we are checking. In
+ * that case, simply insert it there.
+ */
+ if (kind == CHANGE_UPDATE_NEW && tup != tup_key &&
+ is_tuple_in_block_range(tup, ctx->first_block,
+ range_end))
+ apply_concurrent_insert(rel, tup, ctx->iistate,
+ index_slot);
+ }
if (tup_old != NULL)
{
pfree(tup_old);
@@ -2940,6 +3076,33 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target)
pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1);
}
+/*
+ * Check if tuple originates from given range of blocks that have already been
+ * copied.
+ */
+static bool
+is_tuple_in_block_range(HeapTuple tup, BlockNumber start, BlockNumber end)
+{
+ BlockNumber blknum;
+
+ Assert(BlockNumberIsValid(start) && BlockNumberIsValid(end));
+
+ blknum = ItemPointerGetBlockNumber(&tup->t_self);
+ Assert(BlockNumberIsValid(blknum));
+
+ if (start < end)
+ {
+ return blknum >= start && blknum < end;
+ }
+ else
+ {
+ /* Has the scan position wrapped around? */
+ Assert(start > end);
+
+ return blknum >= start || blknum < end;
+ }
+}
+
/*
* Find the tuple to be updated or deleted.
*
@@ -2949,10 +3112,10 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target)
* it when he no longer needs the tuple returned.
*/
static HeapTuple
-find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
- TupleTableSlot *ident_slot)
+find_target_tuple(Relation rel, ConcurrentChangeContext *ctx,
+ HeapTuple tup_key, TupleTableSlot *ident_slot)
{
- Relation ident_index = dest->ident_index;
+ Relation ident_index = ctx->ident_index;
IndexScanDesc scan;
Form_pg_index ident_form;
int2vector *ident_indkey;
@@ -2960,14 +3123,14 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
/* XXX no instrumentation for now */
scan = index_beginscan(rel, ident_index, GetActiveSnapshot(),
- NULL, dest->ident_key_nentries, 0);
+ NULL, ctx->ident_key_nentries, 0);
/*
* Scan key is passed by caller, so it does not have to be constructed
* multiple times. Key entries have all fields initialized, except for
* sk_argument.
*/
- index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
+ index_rescan(scan, ctx->ident_key, ctx->ident_key_nentries, NULL, 0);
/* Info needed to retrieve key values from heap tuple. */
ident_form = ident_index->rd_index;
@@ -3002,15 +3165,22 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key,
}
/*
- * Decode and apply concurrent changes, up to (and including) the record whose
- * LSN is 'end_of_wal'.
+ * Get concurrent changes, up to (and including) the record whose LSN is
+ * 'end_of_wal', from the decoding worker. If 'range_end' is a valid block
+ * number, the changes should only be applied to blocks greater than or equal
+ * to ctx->first_block and lower than range_end.
+ *
+ * If 'request_snapshot' is true, the snapshot built at LSN following the last
+ * data change needs to be exported too.
*/
-static void
-process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
+extern void
+repack_get_concurrent_changes(ConcurrentChangeContext *ctx,
+ XLogRecPtr end_of_wal,
+ BlockNumber range_end,
+ bool request_snapshot, bool done)
{
DecodingWorkerShared *shared;
char fname[MAXPGPATH];
- BufFile *file;
pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
PROGRESS_REPACK_PHASE_CATCH_UP);
@@ -3019,6 +3189,8 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
SpinLockAcquire(&shared->mutex);
shared->lsn_upto = end_of_wal;
+ Assert(!shared->snapshot_requested);
+ shared->snapshot_requested = request_snapshot;
shared->done = done;
SpinLockRelease(&shared->mutex);
@@ -3030,32 +3202,49 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done)
ConditionVariablePrepareToSleep(&shared->cv);
for (;;)
{
- bool valid;
+ int response;
SpinLockAcquire(&shared->mutex);
- valid = shared->sfs_valid;
+ response = shared->response;
SpinLockRelease(&shared->mutex);
- if (valid)
+ if (response & WORKER_RESPONSE_CHANGES)
break;
ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
}
ConditionVariableCancelSleep();
- /* Open the file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
- file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
- apply_concurrent_changes(file, dest);
+ /*
+ * Remember the file name so we can apply the changes when appropriate.
+ * One particular reason to postpone the replay is that indexes haven't
+ * been built yet on the new heap.
+ */
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_changes,
+ false);
+ repack_add_block_range(ctx, range_end, fname);
/* No file is exported until the worker exports the next one. */
SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = false;
+ shared->response &= ~WORKER_RESPONSE_CHANGES;
+ Assert(XLogRecPtrIsInvalid(shared->lsn_upto));
SpinLockRelease(&shared->mutex);
+}
- BufFileClose(file);
+static void
+repack_add_block_range(ConcurrentChangeContext *ctx, BlockNumber end,
+ char *fname)
+{
+ RepackApplyRange *range;
+
+ range = palloc_object(RepackApplyRange);
+ range->end = end;
+ range->fname = pstrdup(fname);
+ ctx->block_ranges = lappend(ctx->block_ranges, range);
}
+
/*
* Initialize IndexInsertState for index specified by ident_index_id.
*
@@ -3198,7 +3387,8 @@ static void
rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation cl_index,
TransactionId frozenXid,
- MultiXactId cutoffMulti)
+ MultiXactId cutoffMulti,
+ ConcurrentChangeContext *ctx)
{
LOCKMODE lockmode_old PG_USED_FOR_ASSERTS_ONLY;
List *ind_oids_new;
@@ -3217,7 +3407,6 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
Relation *ind_refs,
*ind_refs_p;
int nind;
- ChangeDest chgdst;
/* Like in cluster_rel(). */
lockmode_old = ShareUpdateExclusiveLock;
@@ -3274,11 +3463,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
(errmsg("identity index missing on the new relation")));
/* Gather information to apply concurrent changes. */
- chgdst.rel = NewHeap;
- chgdst.iistate = get_index_insert_state(NewHeap, ident_idx_new,
- &chgdst.ident_index);
- chgdst.ident_key = build_identity_key(ident_idx_new, OldHeap,
- &chgdst.ident_key_nentries);
+ ctx->rel = NewHeap;
+ ctx->iistate = get_index_insert_state(NewHeap, ident_idx_new,
+ &ctx->ident_index);
+ ctx->ident_key = build_identity_key(ident_idx_new, OldHeap,
+ &ctx->ident_key_nentries);
+
+ /*
+ * Replay the concurrent data changes gathered during heap copying. This
+ * had to wait until after the index build because the identity index is
+ * needed to apply UPDATE and DELETE changes.
+ */
+ apply_concurrent_changes(ctx);
/*
* During testing, wait for another backend to perform concurrent data
@@ -3296,11 +3492,13 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
end_of_wal = GetFlushRecPtr(NULL);
/*
- * Apply concurrent changes first time, to minimize the time we need to
- * hold AccessExclusiveLock. (Quite some amount of WAL could have been
+ * Decode and apply concurrent changes again, to minimize the time we need
+ * to hold AccessExclusiveLock. (Quite some amount of WAL could have been
* written during the data copying and index creation.)
*/
- process_concurrent_changes(end_of_wal, &chgdst, false);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber, false,
+ false);
+ apply_concurrent_changes(ctx);
/*
* Acquire AccessExclusiveLock on the table, its TOAST relation (if there
@@ -3397,10 +3595,13 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
end_of_wal = GetFlushRecPtr(NULL);
/*
- * Apply the concurrent changes again. Indicate that the decoding worker
- * won't be needed anymore.
+ * Decode and apply the concurrent changes again. Indicate that the
+ * decoding worker won't be needed anymore.
*/
- process_concurrent_changes(end_of_wal, &chgdst, true);
+ repack_get_concurrent_changes(ctx, end_of_wal, InvalidBlockNumber, false,
+ true);
+ apply_concurrent_changes(ctx);
+
/* Remember info about rel before closing OldHeap */
relpersistence = OldHeap->rd_rel->relpersistence;
@@ -3451,8 +3652,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
table_close(NewHeap, NoLock);
/* Cleanup what we don't need anymore. (And close the identity index.) */
- pfree(chgdst.ident_key);
- free_index_insert_state(chgdst.iistate);
+ pfree(ctx->ident_key);
+ free_index_insert_state(ctx->iistate);
/*
* Swap the relations and their TOAST relations and TOAST indexes. This
@@ -3495,6 +3696,23 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
char *newName;
Relation ind;
+ /*
+ * Try to reduce the impact on VACUUM.
+ *
+ * The individual builds might still be a problem, but that's a
+ * separate issue.
+ *
+ * TODO Can we somehow use the fact that the new heap is not yet
+ * visible to other transaction, and thus cannot be vacuumed? Perhaps
+ * by preventing snapshots from setting MyProc->xmin temporarily. (All
+ * the snapshots that might have participated in the build, including
+ * the catalog snapshots, must not be used for other tables of
+ * course.)
+ */
+ PopActiveSnapshot();
+ InvalidateCatalogSnapshot();
+ PushActiveSnapshot(GetTransactionSnapshot());
+
ind_oid = lfirst_oid(lc);
ind = index_open(ind_oid, ShareUpdateExclusiveLock);
@@ -3534,11 +3752,15 @@ start_decoding_worker(Oid relid)
BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
seg = dsm_create(size, 0);
shared = (DecodingWorkerShared *) dsm_segment_address(seg);
+ shared->initialized = false;
shared->lsn_upto = InvalidXLogRecPtr;
shared->done = false;
+ /* Snapshot is the first thing we need from the worker. */
+ shared->snapshot_requested = true;
+ shared->response = 0;
SharedFileSetInit(&shared->sfs, seg);
- shared->sfs_valid = false;
- shared->last_exported = -1;
+ shared->last_exported_changes = -1;
+ shared->last_exported_snapshot = -1;
SpinLockInit(&shared->mutex);
shared->dbid = MyDatabaseId;
@@ -3747,7 +3969,10 @@ repack_worker_internal(dsm_segment *seg)
*/
SpinLockAcquire(&shared->mutex);
Assert(XLogRecPtrIsInvalid(shared->lsn_upto));
- Assert(!shared->sfs_valid);
+ Assert(shared->response == 0);
+ /* Initially we're expected to provide a snapshot and only that. */
+ Assert(shared->snapshot_requested &&
+ XLogRecPtrIsInvalid(shared->lsn_upto));
sfs = &shared->sfs;
SpinLockRelease(&shared->mutex);
@@ -3765,8 +3990,23 @@ repack_worker_internal(dsm_segment *seg)
ConditionVariableSignal(&shared->cv);
/* Build the initial snapshot and export it. */
- snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder);
- export_initial_snapshot(snapshot, shared);
+ snapshot = SnapBuildSnapshotForRepack(decoding_ctx->snapshot_builder);
+ export_snapshot(snapshot, shared);
+
+ /*
+ * Adjust the replication slot's xmin so that VACUUM can do more work.
+ */
+ LogicalIncreaseXminForSlot(InvalidXLogRecPtr, snapshot->xmin, false);
+ FreeSnapshot(snapshot);
+
+ /* Tell the backend that the file is available. */
+ SpinLockAcquire(&shared->mutex);
+ Assert(shared->snapshot_requested);
+ shared->snapshot_requested = false;
+ shared->response |= WORKER_RESPONSE_SNAPSHOT;
+ shared->last_exported_snapshot++;
+ SpinLockRelease(&shared->mutex);
+ ConditionVariableSignal(&shared->cv);
/*
* Only historic snapshots should be used now. Do not let us restrict the
@@ -3786,7 +4026,7 @@ repack_worker_internal(dsm_segment *seg)
* Make snapshot available to the backend that launched the decoding worker.
*/
static void
-export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
+export_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
{
char fname[MAXPGPATH];
BufFile *file;
@@ -3796,29 +4036,23 @@ export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared)
snap_size = EstimateSnapshotSpace(snapshot);
snap_space = (char *) palloc(snap_size);
SerializeSnapshot(snapshot, snap_space);
- FreeSnapshot(snapshot);
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_snapshot + 1,
+ true);
file = BufFileCreateFileSet(&shared->sfs.fs, fname);
/* To make restoration easier, write the snapshot size first. */
BufFileWrite(file, &snap_size, sizeof(snap_size));
BufFileWrite(file, snap_space, snap_size);
pfree(snap_space);
BufFileClose(file);
-
- /* Tell the backend that the file is available. */
- SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = true;
- shared->last_exported++;
- SpinLockRelease(&shared->mutex);
- ConditionVariableSignal(&shared->cv);
}
/*
- * Get the initial snapshot from the decoding worker.
+ * Get snapshot from the decoding worker.
*/
-static Snapshot
-get_initial_snapshot(DecodingWorker *worker)
+extern Snapshot
+repack_get_snapshot(ConcurrentChangeContext *ctx)
{
DecodingWorkerShared *shared;
char fname[MAXPGPATH];
@@ -3826,24 +4060,26 @@ get_initial_snapshot(DecodingWorker *worker)
Size snap_size;
char *snap_space;
Snapshot snapshot;
+ DecodingWorker *worker = ctx->worker;
shared = (DecodingWorkerShared *) dsm_segment_address(worker->seg);
/*
- * The worker needs to initialize the logical decoding, which usually
- * takes some time. Therefore it makes sense to prepare for the sleep
- * first.
+ * For the first snapshot request, the worker needs to initialize the
+ * logical decoding, which usually takes some time. Therefore it makes
+ * sense to prepare for the sleep first. Does it make sense to skip the
+ * preparation on the next requests?
*/
ConditionVariablePrepareToSleep(&shared->cv);
for (;;)
{
- bool valid;
+ int response;
SpinLockAcquire(&shared->mutex);
- valid = shared->sfs_valid;
+ response = shared->response;
SpinLockRelease(&shared->mutex);
- if (valid)
+ if (response & WORKER_RESPONSE_SNAPSHOT)
break;
ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT);
@@ -3851,7 +4087,9 @@ get_initial_snapshot(DecodingWorker *worker)
ConditionVariableCancelSleep();
/* Read the snapshot from a file. */
- DecodingWorkerFileName(fname, shared->relid, shared->last_exported);
+ DecodingWorkerFileName(fname, shared->relid,
+ shared->last_exported_snapshot,
+ true);
file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
BufFileReadExact(file, &snap_size, sizeof(snap_size));
snap_space = (char *) palloc(snap_size);
@@ -3859,7 +4097,8 @@ get_initial_snapshot(DecodingWorker *worker)
BufFileClose(file);
SpinLockAcquire(&shared->mutex);
- shared->sfs_valid = false;
+ shared->response &= ~WORKER_RESPONSE_SNAPSHOT;
+ Assert(!shared->snapshot_requested);
SpinLockRelease(&shared->mutex);
/* Restore it. */
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index a956892f42f..c8bc85d8bcc 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -1003,6 +1003,7 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
xl_heap_insert *xlrec;
ReorderBufferChange *change;
RelFileLocator target_locator;
+ BlockNumber blknum;
xlrec = (xl_heap_insert *) XLogRecGetData(r);
@@ -1014,7 +1015,7 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
return;
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1039,6 +1040,15 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
DecodeXLogTuple(tupledata, datalen, change->data.tp.newtuple);
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the corresponding
+ * part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.newtuple->t_self, blknum,
+ xlrec->offnum);
+
change->data.tp.clear_toast_afterwards = true;
ReorderBufferQueueChange(ctx->reorder, XLogRecGetXid(r), buf->origptr,
@@ -1060,11 +1070,12 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferChange *change;
char *data;
RelFileLocator target_locator;
+ BlockNumber new_blknum;
xlrec = (xl_heap_update *) XLogRecGetData(r);
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &new_blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1090,12 +1101,27 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferAllocTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.newtuple);
+
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the
+ * corresponding part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.newtuple->t_self,
+ new_blknum, xlrec->new_offnum);
}
if (xlrec->flags & XLH_UPDATE_CONTAINS_OLD)
{
Size datalen;
Size tuplelen;
+ BlockNumber old_blknum;
+
+ if (XLogRecHasBlockRef(r, 1))
+ XLogRecGetBlockTag(r, 1, NULL, NULL, &old_blknum);
+ else
+ XLogRecGetBlockTag(r, 0, NULL, NULL, &old_blknum);
/* caution, remaining data in record is not aligned */
data = XLogRecGetData(r) + SizeOfHeapUpdate;
@@ -1106,6 +1132,11 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
ReorderBufferAllocTupleBuf(ctx->reorder, tuplelen);
DecodeXLogTuple(data, datalen, change->data.tp.oldtuple);
+ /* See above. */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ ItemPointerSet(&change->data.tp.oldtuple->t_self,
+ old_blknum, xlrec->old_offnum);
+
}
change->data.tp.clear_toast_afterwards = true;
@@ -1126,11 +1157,12 @@ DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
xl_heap_delete *xlrec;
ReorderBufferChange *change;
RelFileLocator target_locator;
+ BlockNumber blknum;
xlrec = (xl_heap_delete *) XLogRecGetData(r);
/* only interested in our database */
- XLogRecGetBlockTag(r, 0, &target_locator, NULL, NULL);
+ XLogRecGetBlockTag(r, 0, &target_locator, NULL, &blknum);
if (target_locator.dbOid != ctx->slot->data.database)
return;
@@ -1162,6 +1194,15 @@ DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
DecodeXLogTuple((char *) xlrec + SizeOfHeapDelete,
datalen, change->data.tp.oldtuple);
+
+ /*
+ * REPACK (CONCURRENTLY) needs block number to check if the
+ * corresponding part of the table was already copied.
+ */
+ if (OidIsValid(repacked_rel_locator.relNumber))
+ /* offnum is not really needed, but let's set valid pointer. */
+ ItemPointerSet(&change->data.tp.oldtuple->t_self, blknum,
+ xlrec->offnum);
}
change->data.tp.clear_toast_afterwards = true;
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index b3fd7fec392..1e445704a1b 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -1670,14 +1670,17 @@ update_progress_txn_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn,
/*
* Set the required catalog xmin horizon for historic snapshots in the current
- * replication slot.
+ * replication slot if catalog is TRUE, or xmin if catalog is FALSE.
*
* Note that in the most cases, we won't be able to immediately use the xmin
* to increase the xmin horizon: we need to wait till the client has confirmed
- * receiving current_lsn with LogicalConfirmReceivedLocation().
+ * receiving current_lsn with LogicalConfirmReceivedLocation(). However,
+ * catalog=FALSE is only allowed for temporary replication slots, so the
+ * horizon is applied immediately.
*/
void
-LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin)
+LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin,
+ bool catalog)
{
bool updated_xmin = false;
ReplicationSlot *slot;
@@ -1688,6 +1691,27 @@ LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin)
Assert(slot != NULL);
SpinLockAcquire(&slot->mutex);
+ if (!catalog)
+ {
+ /*
+ * The non-catalog horizon can only advance in temporary slots, so
+ * update it in the shared memory immediately (w/o requiring prior
+ * saving to disk).
+ */
+ Assert(slot->data.persistency == RS_TEMPORARY);
+
+ /*
+ * The horizon must not go backwards, however it's o.k. to become
+ * invalid.
+ */
+ Assert(!TransactionIdIsValid(slot->effective_xmin) ||
+ !TransactionIdIsValid(xmin) ||
+ TransactionIdFollowsOrEquals(xmin, slot->effective_xmin));
+
+ slot->effective_xmin = xmin;
+ SpinLockRelease(&slot->mutex);
+ return;
+ }
/*
* don't overwrite if we already have a newer xmin. This can happen if we
diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c
index f18c6fb52b5..273f65d6cc8 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -3734,6 +3734,56 @@ ReorderBufferXidHasCatalogChanges(ReorderBuffer *rb, TransactionId xid)
return rbtxn_has_catalog_changes(txn);
}
+/*
+ * Check if a transaction (or its subtransaction) contains a heap change.
+ */
+bool
+ReorderBufferXidHasHeapChanges(ReorderBuffer *rb, TransactionId xid)
+{
+ ReorderBufferTXN *txn;
+ dlist_iter iter;
+
+ txn = ReorderBufferTXNByXid(rb, xid, false, NULL, InvalidXLogRecPtr,
+ false);
+ if (txn == NULL)
+ return false;
+
+ dlist_foreach(iter, &txn->changes)
+ {
+ ReorderBufferChange *change;
+
+ change = dlist_container(ReorderBufferChange, node, iter.cur);
+
+ switch (change->action)
+ {
+ case REORDER_BUFFER_CHANGE_INSERT:
+ case REORDER_BUFFER_CHANGE_UPDATE:
+ case REORDER_BUFFER_CHANGE_DELETE:
+ return true;
+ default:
+ break;
+ }
+ }
+
+ /* Check subtransactions. */
+
+ /*
+ * TODO Verify that subtransactions must be assigned to the top-level
+ * transactions by now.
+ */
+ dlist_foreach(iter, &txn->subtxns)
+ {
+ ReorderBufferTXN *subtxn;
+
+ subtxn = dlist_container(ReorderBufferTXN, node, iter.cur);
+
+ if (ReorderBufferXidHasHeapChanges(rb, subtxn->xid))
+ return true;
+ }
+
+ return false;
+}
+
/*
* ReorderBufferXidHasBaseSnapshot
* Have we already set the base snapshot for the given txn/subtxn?
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 7643dfe31bb..4bc6cd22496 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -128,6 +128,7 @@
#include "access/heapam_xlog.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "commands/cluster.h"
#include "common/file_utils.h"
#include "miscadmin.h"
#include "pgstat.h"
@@ -496,7 +497,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
* we do not set MyProc->xmin). XXX Do we yet need to add some restrictions?
*/
Snapshot
-SnapBuildInitialSnapshotForRepack(SnapBuild *builder)
+SnapBuildSnapshotForRepack(SnapBuild *builder)
{
Snapshot snap;
@@ -1035,6 +1036,28 @@ SnapBuildCommitTxn(SnapBuild *builder, XLogRecPtr lsn, TransactionId xid,
}
}
+ /*
+ * Is REPACKED (CONCURRENTLY) is being run by this backend?
+ */
+ else if (OidIsValid(repacked_rel_locator.relNumber))
+ {
+ Assert(builder->building_full_snapshot);
+
+ /*
+ * In this special mode, heap changes of other relations should not be
+ * decoded at all - see heap_decode(). Thus if we find a single heap
+ * change in this transaction (or its subtransaction), we know that
+ * this transaction changes the relation being repacked.
+ */
+ if (ReorderBufferXidHasHeapChanges(builder->reorder, xid))
+
+ /*
+ * Record the commit so we can build snapshots for the relation
+ * being repacked.
+ */
+ needs_timetravel = true;
+ }
+
for (nxact = 0; nxact < nsubxacts; nxact++)
{
TransactionId subxid = subxacts[nxact];
@@ -1240,7 +1263,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
xmin = running->oldestRunningXid;
elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
- LogicalIncreaseXminForSlot(lsn, xmin);
+ LogicalIncreaseXminForSlot(lsn, xmin, true);
/*
* Also tell the slot where we can restart decoding from. We don't want to
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index fb9956d392d..be1c3ec9626 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -195,6 +195,8 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len));
/* ... and the tuple itself. */
BufFileWrite(dstate->file, tuple->t_data, tuple->t_len);
+ /* CTID is needed as well, to check block ranges. */
+ BufFileWrite(dstate->file, &tuple->t_self, sizeof(tuple->t_self));
/* Free the flat copy if created above. */
if (flattened)
diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat
index 3b9d8349078..a82d284c44c 100644
--- a/src/backend/utils/misc/guc_parameters.dat
+++ b/src/backend/utils/misc/guc_parameters.dat
@@ -2415,6 +2415,16 @@
boot_val => 'true',
},
+# TODO Tune boot_val, 1024 is probably too low.
+{ name => 'repack_snapshot_after', type => 'int', context => 'PGC_USERSET', group => 'DEVELOPER_OPTIONS',
+ short_desc => 'Number of pages after which REPACK (CONCURRENTLY) builds a new snapshot.',
+ flags => 'GUC_UNIT_BLOCKS | GUC_NOT_IN_SAMPLE',
+ variable => 'repack_blocks_per_snapshot',
+ boot_val => '1024',
+ min => '1',
+ max => 'INT_MAX',
+}
+
{ name => 'reserved_connections', type => 'int', context => 'PGC_POSTMASTER', group => 'CONN_AUTH_SETTINGS',
short_desc => 'Sets the number of connection slots reserved for roles with privileges of pg_use_reserved_connections.',
variable => 'ReservedConnections',
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index f87b558c2c6..07f7cfdd6cc 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -42,6 +42,7 @@
#include "catalog/namespace.h"
#include "catalog/storage.h"
#include "commands/async.h"
+#include "commands/cluster.h"
#include "commands/extension.h"
#include "commands/event_trigger.h"
#include "commands/tablespace.h"
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 321c00682ec..6fe3fc760bc 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -629,12 +629,12 @@ typedef struct TableAmRoutine
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead);
+ double *tups_recently_dead,
+ void *tableam_data);
/*
* React to VACUUM command on the relation. The VACUUM can be triggered by
@@ -1647,8 +1647,6 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator)
* not needed for the relation's AM
* - *xid_cutoff - ditto
* - *multi_cutoff - ditto
- * - snapshot - if != NULL, ignore data changes done by transactions that this
- * (MVCC) snapshot considers still in-progress or in the future.
*
* Output parameters:
* - *xid_cutoff - rel's new relfrozenxid value, may be invalid
@@ -1661,19 +1659,19 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable,
Relation OldIndex,
bool use_sort,
TransactionId OldestXmin,
- Snapshot snapshot,
TransactionId *xid_cutoff,
MultiXactId *multi_cutoff,
double *num_tuples,
double *tups_vacuumed,
- double *tups_recently_dead)
+ double *tups_recently_dead,
+ void *tableam_data)
{
OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex,
use_sort, OldestXmin,
- snapshot,
xid_cutoff, multi_cutoff,
num_tuples, tups_vacuumed,
- tups_recently_dead);
+ tups_recently_dead,
+ tableam_data);
}
/*
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 0ac70ec30d7..2b61dce92dc 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -16,10 +16,12 @@
#include "nodes/execnodes.h"
#include "nodes/parsenodes.h"
#include "parser/parse_node.h"
+#include "postmaster/bgworker.h"
#include "replication/logical.h"
#include "storage/buffile.h"
#include "storage/lock.h"
#include "storage/relfilelocator.h"
+#include "storage/shm_mq.h"
#include "utils/relcache.h"
#include "utils/resowner.h"
#include "utils/tuplestore.h"
@@ -47,6 +49,63 @@ typedef struct ClusterParams
extern RelFileLocator repacked_rel_locator;
extern RelFileLocator repacked_rel_toast_locator;
+extern PGDLLIMPORT int repack_blocks_per_snapshot;
+
+/*
+ * Everything we need to call ExecInsertIndexTuples().
+ */
+typedef struct IndexInsertState
+{
+ ResultRelInfo *rri;
+ EState *estate;
+} IndexInsertState;
+
+/*
+ * Backend-local information to control the decoding worker.
+ */
+typedef struct DecodingWorker
+{
+ /* The worker. */
+ BackgroundWorkerHandle *handle;
+
+ /* DecodingWorkerShared is in this segment. */
+ dsm_segment *seg;
+
+ /* Handle of the error queue. */
+ shm_mq_handle *error_mqh;
+} DecodingWorker;
+
+/*
+ * Information needed to handle concurrent data changes.
+ */
+typedef struct ConcurrentChangeContext
+{
+ /* The relation the changes are applied to. */
+ Relation rel;
+
+ /*
+ * Background worker performing logical decoding of concurrent data
+ * changes.
+ */
+ DecodingWorker *worker;
+
+ /*
+ * The following is needed to find the existing tuple if the change is
+ * UPDATE or DELETE. 'ident_key' should have all the fields except for
+ * 'sk_argument' initialized.
+ */
+ Relation ident_index;
+ ScanKey ident_key;
+ int ident_key_nentries;
+
+ /* Needed to update indexes of rel_dst. */
+ IndexInsertState *iistate;
+
+ /* The first block of the scan used to copy the heap. */
+ BlockNumber first_block;
+ /* List of RepackApplyRange objects. */
+ List *block_ranges;
+} ConcurrentChangeContext;
/*
* Stored as a single byte in the output file.
@@ -102,6 +161,12 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
TransactionId frozenXid,
MultiXactId cutoffMulti,
char newrelpersistence);
+extern void repack_get_concurrent_changes(struct ConcurrentChangeContext *ctx,
+ XLogRecPtr end_of_wal,
+ BlockNumber range_end,
+ bool request_snapshot,
+ bool done);
+extern Snapshot repack_get_snapshot(struct ConcurrentChangeContext *ctx);
extern void RepackWorkerMain(Datum main_arg);
#endif /* CLUSTER_H */
diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h
index 2e562bee5a9..9924f706f20 100644
--- a/src/include/replication/logical.h
+++ b/src/include/replication/logical.h
@@ -137,7 +137,7 @@ extern bool DecodingContextReady(LogicalDecodingContext *ctx);
extern void FreeDecodingContext(LogicalDecodingContext *ctx);
extern void LogicalIncreaseXminForSlot(XLogRecPtr current_lsn,
- TransactionId xmin);
+ TransactionId xmin, bool catalog);
extern void LogicalIncreaseRestartDecodingForSlot(XLogRecPtr current_lsn,
XLogRecPtr restart_lsn);
extern void LogicalConfirmReceivedLocation(XLogRecPtr lsn);
diff --git a/src/include/replication/reorderbuffer.h b/src/include/replication/reorderbuffer.h
index 3cbe106a3c7..b6b739f29f4 100644
--- a/src/include/replication/reorderbuffer.h
+++ b/src/include/replication/reorderbuffer.h
@@ -763,6 +763,7 @@ extern void ReorderBufferProcessXid(ReorderBuffer *rb, TransactionId xid, XLogRe
extern void ReorderBufferXidSetCatalogChanges(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn);
extern bool ReorderBufferXidHasCatalogChanges(ReorderBuffer *rb, TransactionId xid);
+extern bool ReorderBufferXidHasHeapChanges(ReorderBuffer *rb, TransactionId xid);
extern bool ReorderBufferXidHasBaseSnapshot(ReorderBuffer *rb, TransactionId xid);
extern bool ReorderBufferRememberPrepareInfo(ReorderBuffer *rb, TransactionId xid,
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 802fc4b0823..d1f9037fcfb 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,7 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
extern void SnapBuildSnapDecRefcount(Snapshot snap);
extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
-extern Snapshot SnapBuildInitialSnapshotForRepack(SnapBuild *builder);
+extern Snapshot SnapBuildSnapshotForRepack(SnapBuild *builder);
extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
extern void SnapBuildClearExportedSnapshot(void);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 35344910f65..54115135732 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -411,7 +411,6 @@ CatCacheHeader
CatalogId
CatalogIdMapEntry
CatalogIndexState
-ChangeDest
ChangeVarNodes_callback
ChangeVarNodes_context
CheckPoint
@@ -488,6 +487,7 @@ CompressFileHandle
CompressionLocation
CompressorState
ComputeXidHorizonsResult
+ConcurrentChangeContext
ConcurrentChangeKind
ConditionVariable
ConditionVariableMinimallyPadded
@@ -2563,6 +2563,7 @@ ReorderBufferTupleCidKey
ReorderBufferUpdateProgressTxnCB
ReorderTuple
RepOriginId
+RepackApplyRange
RepackCommand
RepackDecodingState
RepackStmt
--
2.47.3
view thread (415+ messages) latest in thread
Message-ID: <210036.1765651719@localhost>
Permalink: ../210036.1765651719@localhost/
Also on: postgresql.org/message-id/210036.1765651719@localhost
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-hackers@postgresql.org
Cc: ah@cybertec.at, alvherre@alvh.no-ip.org, mihailnikalayeu@gmail.com, pgsql-hackers@lists.postgresql.org, rob@xzilla.net
Subject: Re: Adding REPACK [concurrently]
In-Reply-To: <210036.1765651719@localhost>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox