rdelaage
/
postgresql
mirror of https://git.postgresql.org/git/postgresql.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Revert "Fix replay of create database records on standby" 

This reverts commit 49d9cfc68b.  The approach taken by this patch has
problems, so we'll come up with a radically different fix.

Discussion: https://postgr.es/m/CA+TgmoYcUPL+WOJL2ZzhH=zmrhj0iOQ=iCFM0SuYqBbqZEamEg@mail.gmail.com
This commit is contained in:
Alvaro Herrera 2022-03-29 15:36:21 +02:00
parent edea649afb
commit bf902c1393
No known key found for this signature in database
GPG Key ID: 1C20ACB9D5C564AE
7 changed files with 1 additions and 311 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/backend/access/transam/xlogrecovery.c
View File

@ -2047,12 +2047,6 @@ CheckRecoveryConsistency(void)
*/
XLogCheckInvalidPages();
/*
* Check if the XLOG sequence contained any unresolved references to
* missing directories.
*/
XLogCheckMissingDirs();
reachedConsistency = true;
ereport(LOG,
(errmsg("consistent recovery state reached at %X/%X",

159
src/backend/access/transam/xlogutils.c
View File

@ -54,164 +54,6 @@ bool InRecovery = false;
/* Are we in Hot Standby mode? Only valid in startup process, see xlogutils.h */
HotStandbyState standbyState = STANDBY_DISABLED;
/*
* If a create database WAL record is being replayed more than once during
* crash recovery on a standby, it is possible that either the tablespace
* directory or the template database directory is missing. This happens when
* the directories are removed by replay of subsequent drop records. Note
* that this problem happens only on standby and not on master. On master, a
* checkpoint is created at the end of create database operation. On standby,
* however, such a strategy (creating restart points during replay) is not
* viable because it will slow down WAL replay.
*
* The alternative is to track references to each missing directory
* encountered when performing crash recovery in the following hash table.
* Similar to invalid page table above, the expectation is that each missing
* directory entry should be matched with a drop database or drop tablespace
* WAL record by the end of crash recovery.
*/
typedef struct xl_missing_dir_key
{
Oid spcNode;
Oid dbNode;
} xl_missing_dir_key;
typedef struct xl_missing_dir
{
xl_missing_dir_key key;
char path[MAXPGPATH];
} xl_missing_dir;
static HTAB *missing_dir_tab = NULL;
/*
* Keep track of a directory that wasn't found while replaying database
* creation records. These should match up with tablespace removal records
* later in the WAL stream; we verify that before reaching consistency.
*/
void
XLogRememberMissingDir(Oid spcNode, Oid dbNode, char *path)
{
xl_missing_dir_key key;
bool found;
xl_missing_dir *entry;
/*
* Database OID may be invalid but tablespace OID must be valid. If
* dbNode is InvalidOid, we are logging a missing tablespace directory,
* otherwise we are logging a missing database directory.
*/
Assert(OidIsValid(spcNode));
if (missing_dir_tab == NULL)
{
/* create hash table when first needed */
HASHCTL ctl;
memset(&ctl, 0, sizeof(ctl));
ctl.keysize = sizeof(xl_missing_dir_key);
ctl.entrysize = sizeof(xl_missing_dir);
missing_dir_tab = hash_create("XLOG missing directory table",
100,
&ctl,
HASH_ELEM | HASH_BLOBS);
}
key.spcNode = spcNode;
key.dbNode = dbNode;
entry = hash_search(missing_dir_tab, &key, HASH_ENTER, &found);
if (found)
{
if (dbNode == InvalidOid)
elog(DEBUG1, "missing directory %s (tablespace %u) already exists: %s",
path, spcNode, entry->path);
else
elog(DEBUG1, "missing directory %s (tablespace %u database %u) already exists: %s",
path, spcNode, dbNode, entry->path);
}
else
{
strlcpy(entry->path, path, sizeof(entry->path));
if (dbNode == InvalidOid)
elog(DEBUG1, "logged missing dir %s (tablespace %u)",
path, spcNode);
else
elog(DEBUG1, "logged missing dir %s (tablespace %u database %u)",
path, spcNode, dbNode);
}
}
/*
* Remove an entry from the list of directories not found. This is to be done
* when the matching tablespace removal WAL record is found.
*/
void
XLogForgetMissingDir(Oid spcNode, Oid dbNode)
{
xl_missing_dir_key key;
key.spcNode = spcNode;
key.dbNode = dbNode;
/* Database OID may be invalid but tablespace OID must be valid. */
Assert(OidIsValid(spcNode));
if (missing_dir_tab == NULL)
return;
if (hash_search(missing_dir_tab, &key, HASH_REMOVE, NULL) != NULL)
{
if (dbNode == InvalidOid)
{
elog(DEBUG2, "forgot missing dir (tablespace %u)", spcNode);
}
else
{
char *path = GetDatabasePath(dbNode, spcNode);
elog(DEBUG2, "forgot missing dir %s (tablespace %u database %u)",
path, spcNode, dbNode);
pfree(path);
}
}
}
/*
* This is called at the end of crash recovery, before entering archive
* recovery on a standby. PANIC if the hash table is not empty.
*/
void
XLogCheckMissingDirs(void)
{
HASH_SEQ_STATUS status;
xl_missing_dir *hentry;
bool foundone = false;
if (missing_dir_tab == NULL)
return; /* nothing to do */
hash_seq_init(&status, missing_dir_tab);
while ((hentry = (xl_missing_dir *) hash_seq_search(&status)) != NULL)
{
elog(WARNING, "missing directory \"%s\" tablespace %u database %u",
hentry->path, hentry->key.spcNode, hentry->key.dbNode);
foundone = true;
}
if (foundone)
elog(PANIC, "WAL contains references to missing directories");
hash_destroy(missing_dir_tab);
missing_dir_tab = NULL;
}
/*
* During XLOG replay, we may see XLOG records for incremental updates of
* pages that no longer exist, because their relation was later dropped or
@ -237,6 +79,7 @@ typedef struct xl_invalid_page
static HTAB *invalid_page_tab = NULL;
/* Report a reference to an invalid page */
static void
report_invalid_page(int elevel, RelFileNode node, ForkNumber forkno,

57
src/backend/commands/dbcommands.c
View File

@ -30,7 +30,6 @@
#include "access/tableam.h"
#include "access/xact.h"
#include "access/xloginsert.h"
#include "access/xlogrecovery.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
@ -2484,9 +2483,7 @@ dbase_redo(XLogReaderState *record)
xl_dbase_create_rec *xlrec = (xl_dbase_create_rec *) XLogRecGetData(record);
char *src_path;
char *dst_path;
char *parent_path;
struct stat st;
bool skip = false;
src_path = GetDatabasePath(xlrec->src_db_id, xlrec->src_tablespace_id);
dst_path = GetDatabasePath(xlrec->db_id, xlrec->tablespace_id);
@ -2504,56 +2501,6 @@ dbase_redo(XLogReaderState *record)
(errmsg("some useless files may be left behind in old database directory \"%s\"",
dst_path)));
}
else if (!reachedConsistency)
{
/*
* It is possible that a drop tablespace record appearing later in
* WAL has already been replayed -- in other words, that we are
* replaying the database creation record a second time with no
* intervening checkpoint. In that case, the tablespace directory
* has already been removed and the create database operation
* cannot be replayed. Skip the replay itself, but remember the
* fact that the tablespace directory is missing, to be matched
* with the expected tablespace drop record later.
*/
parent_path = pstrdup(dst_path);
get_parent_directory(parent_path);
if (!(stat(parent_path, &st) == 0 && S_ISDIR(st.st_mode)))
{
XLogRememberMissingDir(xlrec->tablespace_id, InvalidOid, parent_path);
skip = true;
ereport(WARNING,
(errmsg("skipping replay of database creation WAL record"),
errdetail("The target tablespace \"%s\" directory was not found.",
parent_path),
errhint("A future WAL record that removes the directory before reaching consistent mode is expected.")));
}
pfree(parent_path);
}
/*
* If the source directory is missing, skip the copy and make a note of
* it for later.
*
* One possible reason for this is that the template database used for
* creating this database may have been dropped, as noted above.
* Moving a database from one tablespace may also be a partner in the
* crime.
*/
if (!(stat(src_path, &st) == 0 && S_ISDIR(st.st_mode)) &&
!reachedConsistency)
{
XLogRememberMissingDir(xlrec->src_tablespace_id, xlrec->src_db_id, src_path);
skip = true;
ereport(WARNING,
(errmsg("skipping replay of database creation WAL record"),
errdetail("The source database directory \"%s\" was not found.",
src_path),
errhint("A future WAL record that removes the directory before reaching consistent mode is expected.")));
}
if (skip)
return;
/*
* Force dirty buffers out to disk, to ensure source database is
@ -2616,10 +2563,6 @@ dbase_redo(XLogReaderState *record)
ereport(WARNING,
(errmsg("some useless files may be left behind in old database directory \"%s\"",
dst_path)));
if (!reachedConsistency)
XLogForgetMissingDir(xlrec->tablespace_ids[i], xlrec->db_id);
pfree(dst_path);
}

17
src/backend/commands/tablespace.c
View File

@ -57,7 +57,6 @@
#include "access/tableam.h"
#include "access/xact.h"
#include "access/xloginsert.h"
#include "access/xlogrecovery.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
@ -1575,22 +1574,6 @@ tblspc_redo(XLogReaderState *record)
{
xl_tblspc_drop_rec *xlrec = (xl_tblspc_drop_rec *) XLogRecGetData(record);
if (!reachedConsistency)
XLogForgetMissingDir(xlrec->ts_id, InvalidOid);
/*
* Before we remove the tablespace directory, update minimum recovery
* point to cover this WAL record. Once the tablespace is removed,
* there's no going back. This manually enforces the WAL-first rule.
* Doing this before the removal means that if the removal fails for
* some reason, the directory is left alone and needs to be manually
* removed. Alternatively we could update the minimum recovery point
* after removal, but that would leave a small window where the
* WAL-first rule could be violated.
*/
if (!reachedConsistency)
XLogFlush(record->EndRecPtr);
/*
* If we issued a WAL record for a drop tablespace it implies that
* there were no files in it at all when the DROP was done. That means

4
src/include/access/xlogutils.h
View File

@ -65,10 +65,6 @@ extern void XLogDropDatabase(Oid dbid);
extern void XLogTruncateRelation(RelFileNode rnode, ForkNumber forkNum,
BlockNumber nblocks);
extern void XLogRememberMissingDir(Oid spcNode, Oid dbNode, char *path);
extern void XLogForgetMissingDir(Oid spcNode, Oid dbNode);
extern void XLogCheckMissingDirs(void);
/* Result codes for XLogReadBufferForRedo[Extended] */
typedef enum
{

67
src/test/recovery/t/029_replay_tsp_drops.pl
View File

@ -1,67 +0,0 @@
# Copyright (c) 2022, PostgreSQL Global Development Group
# Test recovery involving tablespace removal. If recovery stops
# after once tablespace is removed, the next recovery should properly
# ignore the operations within the removed tablespaces.
use strict;
use warnings;
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node_primary = PostgreSQL::Test::Cluster->new('primary1');
$node_primary->init(allows_streaming => 1);
$node_primary->start;
$node_primary->psql('postgres',
qq[
SET allow_in_place_tablespaces=on;
CREATE TABLESPACE dropme_ts1 LOCATION '';
CREATE TABLESPACE dropme_ts2 LOCATION '';
CREATE TABLESPACE source_ts LOCATION '';
CREATE TABLESPACE target_ts LOCATION '';
CREATE DATABASE template_db IS_TEMPLATE = true;
]);
my $backup_name = 'my_backup';
$node_primary->backup($backup_name);
my $node_standby = PostgreSQL::Test::Cluster->new('standby1');
$node_standby->init_from_backup($node_primary, $backup_name, has_streaming => 1);
$node_standby->start;
# Make sure connection is made
$node_primary->poll_query_until(
'postgres', 'SELECT count(*) = 1 FROM pg_stat_replication');
$node_standby->safe_psql('postgres', 'CHECKPOINT');
# Do immediate shutdown just after a sequence of CREATE DATABASE / DROP
# DATABASE / DROP TABLESPACE. This causes CREATE DATABASE WAL records
# to be applied to already-removed directories.
$node_primary->safe_psql('postgres',
q[CREATE DATABASE dropme_db1 WITH TABLESPACE dropme_ts1;
CREATE DATABASE dropme_db2 WITH TABLESPACE dropme_ts2;
CREATE DATABASE moveme_db TABLESPACE source_ts;
ALTER DATABASE moveme_db SET TABLESPACE target_ts;
CREATE DATABASE newdb TEMPLATE template_db;
ALTER DATABASE template_db IS_TEMPLATE = false;
DROP DATABASE dropme_db1;
DROP DATABASE dropme_db2; DROP TABLESPACE dropme_ts2;
DROP TABLESPACE source_ts;
DROP DATABASE template_db;]);
$node_primary->wait_for_catchup($node_standby, 'replay',
$node_primary->lsn('replay'));
$node_standby->stop('immediate');
# Should restart ignoring directory creation error.
is($node_standby->start, 1, "standby started successfully");
my $log = PostgreSQL::Test::Utils::slurp_file($node_standby->logfile);
like(
$log,
qr[WARNING: skipping replay of database creation WAL record],
"warning message is logged");
done_testing();

2
src/tools/pgindent/typedefs.list
View File

@ -3740,8 +3740,6 @@ xl_invalid_page
xl_invalid_page_key
xl_invalidations
xl_logical_message
xl_missing_dir_key
xl_missing_dir
xl_multi_insert_tuple
xl_multixact_create
xl_multixact_truncate