The current implementation of copydir function is incompatible with LSN based incremental backups. The problem is that new files are created, but their blocks are still with the old LSN, so they will not be backed up because they are looking old enough.
copydir function is used in: CREATE DATABASE ALTER DATABASE SET TABLESPACE I can imagine two possible solutions: a) wal log the whole copydir operations, setting the lsn accordingly b) pass to copydir the LSN of the operation which triggered it, and update the LSN of all the copied blocks The latter solution is IMO easier to be implemented and does not deviate much from the current implementation. I've implemented it and it's attached to this message. I've also moved the parse_filename_for_notntemp_relation function out of reinit.c to make it available both to copydir.c and basebackup.c. I've also limited the LSN comparison to the only MAIN fork, because: * LSN fork doesn't uses LSN * VM fork update LSN only when the visibility bit is set * INIT forks doesn't use LSN. It's only one page anyway. Regards, Marco -- Marco Nenciarini - 2ndQuadrant Italy PostgreSQL Training, Services and Support marco.nenciar...@2ndquadrant.it | www.2ndQuadrant.it
From 087faed899b9afab324aff7fa20e715c4f99eb4a Mon Sep 17 00:00:00 2001
From: Marco Nenciarini <marco.nenciar...@2ndquadrant.it>
Date: Thu, 29 Jan 2015 12:18:47 +0100
Subject: [PATCH 1/3] public parse_filename_for_nontemp_relation
---
src/backend/storage/file/reinit.c | 58 ---------------------------------------
src/common/relpath.c | 56 +++++++++++++++++++++++++++++++++++++
src/include/common/relpath.h | 2 ++
3 files changed, 58 insertions(+), 58 deletions(-)
diff --git a/src/backend/storage/file/reinit.c
b/src/backend/storage/file/reinit.c
index afd9255..02b5fee 100644
*** a/src/backend/storage/file/reinit.c
--- b/src/backend/storage/file/reinit.c
*************** static void ResetUnloggedRelationsInTabl
*** 28,35 ****
int
op);
static void ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname,
int op);
- static bool parse_filename_for_nontemp_relation(const char *name,
- int
*oidchars, ForkNumber *fork);
typedef struct
{
--- 28,33 ----
*************** ResetUnloggedRelationsInDbspaceDir(const
*** 388,446 ****
fsync_fname((char *) dbspacedirname, true);
}
}
-
- /*
- * Basic parsing of putative relation filenames.
- *
- * This function returns true if the file appears to be in the correct format
- * for a non-temporary relation and false otherwise.
- *
- * NB: If this function returns true, the caller is entitled to assume that
- * *oidchars has been set to the a value no more than OIDCHARS, and thus
- * that a buffer of OIDCHARS+1 characters is sufficient to hold the OID
- * portion of the filename. This is critical to protect against a possible
- * buffer overrun.
- */
- static bool
- parse_filename_for_nontemp_relation(const char *name, int *oidchars,
-
ForkNumber *fork)
- {
- int pos;
-
- /* Look for a non-empty string of digits (that isn't too long). */
- for (pos = 0; isdigit((unsigned char) name[pos]); ++pos)
- ;
- if (pos == 0 || pos > OIDCHARS)
- return false;
- *oidchars = pos;
-
- /* Check for a fork name. */
- if (name[pos] != '_')
- *fork = MAIN_FORKNUM;
- else
- {
- int forkchar;
-
- forkchar = forkname_chars(&name[pos + 1], fork);
- if (forkchar <= 0)
- return false;
- pos += forkchar + 1;
- }
-
- /* Check for a segment number. */
- if (name[pos] == '.')
- {
- int segchar;
-
- for (segchar = 1; isdigit((unsigned char) name[pos + segchar]);
++segchar)
- ;
- if (segchar <= 1)
- return false;
- pos += segchar;
- }
-
- /* Now we should be at the end. */
- if (name[pos] != '\0')
- return false;
- return true;
- }
--- 386,388 ----
diff --git a/src/common/relpath.c b/src/common/relpath.c
index 66dfef1..83a1e3a 100644
*** a/src/common/relpath.c
--- b/src/common/relpath.c
*************** GetRelationPath(Oid dbNode, Oid spcNode,
*** 206,208 ****
--- 206,264 ----
}
return path;
}
+
+ /*
+ * Basic parsing of putative relation filenames.
+ *
+ * This function returns true if the file appears to be in the correct format
+ * for a non-temporary relation and false otherwise.
+ *
+ * NB: If this function returns true, the caller is entitled to assume that
+ * *oidchars has been set to the a value no more than OIDCHARS, and thus
+ * that a buffer of OIDCHARS+1 characters is sufficient to hold the OID
+ * portion of the filename. This is critical to protect against a possible
+ * buffer overrun.
+ */
+ bool
+ parse_filename_for_nontemp_relation(const char *name, int *oidchars,
+
ForkNumber *fork)
+ {
+ int pos;
+
+ /* Look for a non-empty string of digits (that isn't too long). */
+ for (pos = 0; isdigit((unsigned char) name[pos]); ++pos)
+ ;
+ if (pos == 0 || pos > OIDCHARS)
+ return false;
+ *oidchars = pos;
+
+ /* Check for a fork name. */
+ if (name[pos] != '_')
+ *fork = MAIN_FORKNUM;
+ else
+ {
+ int forkchar;
+
+ forkchar = forkname_chars(&name[pos + 1], fork);
+ if (forkchar <= 0)
+ return false;
+ pos += forkchar + 1;
+ }
+
+ /* Check for a segment number. */
+ if (name[pos] == '.')
+ {
+ int segchar;
+
+ for (segchar = 1; isdigit((unsigned char) name[pos + segchar]);
++segchar)
+ ;
+ if (segchar <= 1)
+ return false;
+ pos += segchar;
+ }
+
+ /* Now we should be at the end. */
+ if (name[pos] != '\0')
+ return false;
+ return true;
+ }
diff --git a/src/include/common/relpath.h b/src/include/common/relpath.h
index a263779..9736a78 100644
*** a/src/include/common/relpath.h
--- b/src/include/common/relpath.h
*************** extern char *GetDatabasePath(Oid dbNode,
*** 52,57 ****
--- 52,59 ----
extern char *GetRelationPath(Oid dbNode, Oid spcNode, Oid relNode,
int backendId, ForkNumber forkNumber);
+ extern bool parse_filename_for_nontemp_relation(const char *name,
+ int *oidchars,
ForkNumber *fork);
/*
* Wrapper macros for GetRelationPath. Beware of multiple
--
2.2.2
From a4952a2fe57f26e50cfc14de0286e1466caaa4ae Mon Sep 17 00:00:00 2001
From: Marco Nenciarini <marco.nenciar...@2ndquadrant.it>
Date: Thu, 29 Jan 2015 11:41:35 +0100
Subject: [PATCH 2/3] copydir LSN
---
src/backend/commands/dbcommands.c | 32 ++++++++++++----------
src/backend/storage/file/copydir.c | 56 +++++++++++++++++++++++++++++++++++---
src/backend/storage/file/reinit.c | 3 +-
src/include/storage/copydir.h | 6 ++--
4 files changed, 76 insertions(+), 21 deletions(-)
diff --git a/src/backend/commands/dbcommands.c
b/src/backend/commands/dbcommands.c
index 5e66961..6dd9878 100644
*** a/src/backend/commands/dbcommands.c
--- b/src/backend/commands/dbcommands.c
*************** createdb(const CreatedbStmt *stmt)
*** 586,591 ****
--- 586,592 ----
Oid dsttablespace;
char *srcpath;
char *dstpath;
+ XLogRecPtr recptr;
struct stat st;
/* No need to copy global tablespace */
*************** createdb(const CreatedbStmt *stmt)
*** 609,621 ****
dstpath = GetDatabasePath(dboid, dsttablespace);
- /*
- * Copy this subdirectory to the new location
- *
- * We don't need to copy subdirectories
- */
- copydir(srcpath, dstpath, false);
-
/* Record the filesystem change in XLOG */
{
xl_dbase_create_rec xlrec;
--- 610,615 ----
*************** createdb(const CreatedbStmt *stmt)
*** 628,636 ****
XLogBeginInsert();
XLogRegisterData((char *) &xlrec,
sizeof(xl_dbase_create_rec));
! (void) XLogInsert(RM_DBASE_ID,
XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE);
}
}
heap_endscan(scan);
heap_close(rel, AccessShareLock);
--- 622,637 ----
XLogBeginInsert();
XLogRegisterData((char *) &xlrec,
sizeof(xl_dbase_create_rec));
! recptr = XLogInsert(RM_DBASE_ID,
XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE);
}
+
+ /*
+ * Copy this subdirectory to the new location
+ *
+ * We don't need to copy subdirectories
+ */
+ copydir(srcpath, dstpath, false, recptr);
}
heap_endscan(scan);
heap_close(rel, AccessShareLock);
*************** movedb(const char *dbname, const char *t
*** 1214,1223 ****
PG_ENSURE_ERROR_CLEANUP(movedb_failure_callback,
PointerGetDatum(&fparms));
{
! /*
! * Copy files from the old tablespace to the new one
! */
! copydir(src_dbpath, dst_dbpath, false);
/*
* Record the filesystem change in XLOG
--- 1215,1221 ----
PG_ENSURE_ERROR_CLEANUP(movedb_failure_callback,
PointerGetDatum(&fparms));
{
! XLogRecPtr recptr;
/*
* Record the filesystem change in XLOG
*************** movedb(const char *dbname, const char *t
*** 1233,1243 ****
XLogBeginInsert();
XLogRegisterData((char *) &xlrec,
sizeof(xl_dbase_create_rec));
! (void) XLogInsert(RM_DBASE_ID,
XLOG_DBASE_CREATE |
XLR_SPECIAL_REL_UPDATE);
}
/*
* Update the database's pg_database tuple
*/
ScanKeyInit(&scankey,
--- 1231,1246 ----
XLogBeginInsert();
XLogRegisterData((char *) &xlrec,
sizeof(xl_dbase_create_rec));
! recptr = XLogInsert(RM_DBASE_ID,
XLOG_DBASE_CREATE |
XLR_SPECIAL_REL_UPDATE);
}
/*
+ * Copy files from the old tablespace to the new one
+ */
+ copydir(src_dbpath, dst_dbpath, false, recptr);
+
+ /*
* Update the database's pg_database tuple
*/
ScanKeyInit(&scankey,
*************** dbase_redo(XLogReaderState *record)
*** 2045,2050 ****
--- 2048,2054 ----
if (info == XLOG_DBASE_CREATE)
{
xl_dbase_create_rec *xlrec = (xl_dbase_create_rec *)
XLogRecGetData(record);
+ XLogRecPtr lsn = record->EndRecPtr;
char *src_path;
char *dst_path;
struct stat st;
*************** dbase_redo(XLogReaderState *record)
*** 2077,2083 ****
*
* We don't need to copy subdirectories
*/
! copydir(src_path, dst_path, false);
}
else if (info == XLOG_DBASE_DROP)
{
--- 2081,2087 ----
*
* We don't need to copy subdirectories
*/
! copydir(src_path, dst_path, false, lsn);
}
else if (info == XLOG_DBASE_DROP)
{
diff --git a/src/backend/storage/file/copydir.c
b/src/backend/storage/file/copydir.c
index 41b2c62..92b49ab 100644
*** a/src/backend/storage/file/copydir.c
--- b/src/backend/storage/file/copydir.c
***************
*** 22,27 ****
--- 22,29 ----
#include <unistd.h>
#include <sys/stat.h>
+ #include "common/relpath.h"
+ #include "storage/bufpage.h"
#include "storage/copydir.h"
#include "storage/fd.h"
#include "miscadmin.h"
***************
*** 32,40 ****
*
* If recurse is false, subdirectories are ignored. Anything that's not
* a directory or a regular file is ignored.
*/
void
! copydir(char *fromdir, char *todir, bool recurse)
{
DIR *xldir;
struct dirent *xlde;
--- 34,45 ----
*
* If recurse is false, subdirectories are ignored. Anything that's not
* a directory or a regular file is ignored.
+ *
+ * If recptr is different from InvalidXlogRecPtr, LSN of pages in the
+ * destination directory will be updated to recptr.
*/
void
! copydir(char *fromdir, char *todir, bool recurse, XLogRecPtr recptr)
{
DIR *xldir;
struct dirent *xlde;
*************** copydir(char *fromdir, char *todir, bool
*** 75,84 ****
{
/* recurse to handle subdirectories */
if (recurse)
! copydir(fromfile, tofile, true);
}
else if (S_ISREG(fst.st_mode))
! copy_file(fromfile, tofile);
}
FreeDir(xldir);
--- 80,106 ----
{
/* recurse to handle subdirectories */
if (recurse)
! copydir(fromfile, tofile, true, recptr);
}
else if (S_ISREG(fst.st_mode))
! {
! int oidchars;
! ForkNumber fork;
!
! /*
! * To support incremental backups, we need to update
the LSN in
! * all relation files we are copying.
! *
! * We are updating only the MAIN fork because at the
moment
! * blocks in FSM and VM forks are not guaranteed to
have an
! * up-to-date LSN
! */
! if (parse_filename_for_nontemp_relation(xlde->d_name,
! &oidchars, &fork) && fork ==
MAIN_FORKNUM)
! copy_file(fromfile, tofile, recptr);
! else
! copy_file(fromfile, tofile, InvalidXLogRecPtr);
! }
}
FreeDir(xldir);
*************** copydir(char *fromdir, char *todir, bool
*** 130,138 ****
/*
* copy one file
*/
void
! copy_file(char *fromfile, char *tofile)
{
char *buffer;
int srcfd;
--- 152,163 ----
/*
* copy one file
+ *
+ * If recptr is different from InvalidXlogRecPtr, the destination file will
+ * have all its pages with LSN set accordingly
*/
void
! copy_file(char *fromfile, char *tofile, XLogRecPtr recptr)
{
char *buffer;
int srcfd;
*************** copy_file(char *fromfile, char *tofile)
*** 176,181 ****
--- 201,229 ----
errmsg("could not read file \"%s\":
%m", fromfile)));
if (nbytes == 0)
break;
+
+ /*
+ * If a valid recptr has been provided, the resulting file will
have
+ * all its pages with LSN set accordingly
+ */
+ if (recptr != InvalidXLogRecPtr)
+ {
+ char *page;
+
+ /*
+ * If we are updating LSN of a file, we must be sure
that the
+ * source file is not being extended.
+ */
+ if (nbytes % BLCKSZ != 0)
+ ereport(ERROR,
+
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("file \"%s\" size is
not multiple of %d",
+ fromfile,
BLCKSZ)));
+
+ for (page = buffer; page < (buffer + nbytes); page +=
BLCKSZ)
+ PageSetLSN(page, recptr);
+ }
+
errno = 0;
if ((int) write(dstfd, buffer, nbytes) != nbytes)
{
diff --git a/src/backend/storage/file/reinit.c
b/src/backend/storage/file/reinit.c
index 02b5fee..854ae4a 100644
*** a/src/backend/storage/file/reinit.c
--- b/src/backend/storage/file/reinit.c
***************
*** 16,21 ****
--- 16,22 ----
#include <unistd.h>
+ #include "access/xlogdefs.h"
#include "catalog/catalog.h"
#include "common/relpath.h"
#include "storage/copydir.h"
*************** ResetUnloggedRelationsInDbspaceDir(const
*** 333,339 ****
/* OK, we're ready to perform the actual copy. */
elog(DEBUG2, "copying %s to %s", srcpath, dstpath);
! copy_file(srcpath, dstpath);
}
FreeDir(dbspace_dir);
--- 334,340 ----
/* OK, we're ready to perform the actual copy. */
elog(DEBUG2, "copying %s to %s", srcpath, dstpath);
! copy_file(srcpath, dstpath, InvalidXLogRecPtr);
}
FreeDir(dbspace_dir);
diff --git a/src/include/storage/copydir.h b/src/include/storage/copydir.h
index 2635a7e..463141d 100644
*** a/src/include/storage/copydir.h
--- b/src/include/storage/copydir.h
***************
*** 13,19 ****
#ifndef COPYDIR_H
#define COPYDIR_H
! extern void copydir(char *fromdir, char *todir, bool recurse);
! extern void copy_file(char *fromfile, char *tofile);
#endif /* COPYDIR_H */
--- 13,21 ----
#ifndef COPYDIR_H
#define COPYDIR_H
! #include "access/xlogdefs.h"
!
! extern void copydir(char *fromdir, char *todir, bool recurse, XLogRecPtr
recptr);
! extern void copy_file(char *fromfile, char *tofile, XLogRecPtr recptr);
#endif /* COPYDIR_H */
--
2.2.2
From 99a0ee4950a77ae6fbe35d294d47b53a273496a6 Mon Sep 17 00:00:00 2001
From: Marco Nenciarini <marco.nenciar...@2ndquadrant.it>
Date: Tue, 14 Oct 2014 14:31:28 +0100
Subject: [PATCH 3/3] File-based incremental backup v8
Add backup profiles and --incremental to pg_basebackup
---
doc/src/sgml/protocol.sgml | 86 ++++++++-
doc/src/sgml/ref/pg_basebackup.sgml | 31 +++-
src/backend/access/transam/xlog.c | 18 +-
src/backend/access/transam/xlogfuncs.c | 2 +-
src/backend/replication/basebackup.c | 319 +++++++++++++++++++++++++++++++--
src/backend/replication/repl_gram.y | 6 +
src/backend/replication/repl_scanner.l | 1 +
src/bin/pg_basebackup/pg_basebackup.c | 191 ++++++++++++++++++--
src/include/access/xlog.h | 3 +-
src/include/replication/basebackup.h | 5 +
10 files changed, 623 insertions(+), 39 deletions(-)
diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml
index efe75ea..fc24648 100644
*** a/doc/src/sgml/protocol.sgml
--- b/doc/src/sgml/protocol.sgml
*************** The commands accepted in walsender mode
*** 1882,1888 ****
</varlistentry>
<varlistentry>
! <term>BASE_BACKUP [<literal>LABEL</literal>
<replaceable>'label'</replaceable>] [<literal>PROGRESS</literal>]
[<literal>FAST</literal>] [<literal>WAL</literal>] [<literal>NOWAIT</literal>]
[<literal>MAX_RATE</literal> <replaceable>rate</replaceable>]
<indexterm><primary>BASE_BACKUP</primary></indexterm>
</term>
<listitem>
--- 1882,1888 ----
</varlistentry>
<varlistentry>
! <term>BASE_BACKUP [<literal>LABEL</literal>
<replaceable>'label'</replaceable>] [<literal>INCREMENTAL</literal>
<replaceable>'start_lsn'</replaceable>] [<literal>PROGRESS</literal>]
[<literal>FAST</literal>] [<literal>WAL</literal>] [<literal>NOWAIT</literal>]
[<literal>MAX_RATE</literal> <replaceable>rate</replaceable>]
<indexterm><primary>BASE_BACKUP</primary></indexterm>
</term>
<listitem>
*************** The commands accepted in walsender mode
*** 1905,1910 ****
--- 1905,1928 ----
</varlistentry>
<varlistentry>
+ <term><literal>INCREMENTAL</literal>
<replaceable>'start_lsn'</replaceable></term>
+ <listitem>
+ <para>
+ Requests a file-level incremental backup of all files changed after
+ <replaceable>start_lsn</replaceable>. When operating with
+ <literal>INCREMENTAL</literal>, the content of every block-organised
+ file will be analyzed and the file will be sent if at least one
+ block has a LSN higher than or equal to the provided
+ <replaceable>start_lsn</replaceable>.
+ </para>
+ <para>
+ The <filename>backup_profile</filename> will contain information on
+ every file that has been analyzed, even those that have not been
sent.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
<term><literal>PROGRESS</></term>
<listitem>
<para>
*************** The commands accepted in walsender mode
*** 2022,2028 ****
<quote>ustar interchange format</> specified in the POSIX 1003.1-2008
standard) dump of the tablespace contents, except that the two trailing
blocks of zeroes specified in the standard are omitted.
! After the tar data is complete, a final ordinary result set will be
sent,
containing the WAL end position of the backup, in the same format as
the start position.
</para>
--- 2040,2046 ----
<quote>ustar interchange format</> specified in the POSIX 1003.1-2008
standard) dump of the tablespace contents, except that the two trailing
blocks of zeroes specified in the standard are omitted.
! After the tar data is complete, an ordinary result set will be sent,
containing the WAL end position of the backup, in the same format as
the start position.
</para>
*************** The commands accepted in walsender mode
*** 2073,2082 ****
the server supports it.
</para>
<para>
! Once all tablespaces have been sent, a final regular result set will
be sent. This result set contains the end position of the
backup, given in XLogRecPtr format as a single column in a single row.
</para>
</listitem>
</varlistentry>
</variablelist>
--- 2091,2162 ----
the server supports it.
</para>
<para>
! Once all tablespaces have been sent, another regular result set will
be sent. This result set contains the end position of the
backup, given in XLogRecPtr format as a single column in a single row.
</para>
+ <para>
+ Finally a last CopyResponse will be sent, containing only the
+ <filename>backup_profile</filename> file, in tar format.
+ </para>
+ <para>
+ The <filename>backup_profile</filename> file will have the following
+ format:
+ <programlisting>
+ POSTGRESQL BACKUP PROFILE 1
+ <backup label content>
+ FILE LIST
+ <file list>
+ </programlisting>
+ where <replaceable><backup label content></replaceable> is a
+ verbatim copy of the content of <filename>backup_label</filename> file
+ and the <replaceable><file list></replaceable> section is made up
+ of one line per file examined by the backup, having the following format
+ (standard COPY TEXT file, tab separated):
+ <programlisting>
+ tablespace maxlsn included mtime size relpath
+ </programlisting>
+ </para>
+ <para>
+ The meaning of the fields is the following:
+ <itemizedlist spacing="compact" mark="bullet">
+ <listitem>
+ <para>
+ <replaceable>tablespace</replaceable> is the OID of the tablespace
+ (or <literal>\N</literal> for files in PGDATA)
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <replaceable>maxlsn</replaceable> is the file's max LSN in case
+ the file has been skipped, <literal>\N</literal> otherwise
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <replaceable>included</replaceable> is a <literal>'t'</literal> if
+ the file is included in the backup, <literal>'f'</literal> otherwise
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <replaceable>mtime</replaceable> is the timestamp of the last file
+ modification
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <replaceable>size</replaceable> is the number of bytes of the file
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <replaceable>relpath</replaceable> is the path of the file relative
+ to the tablespace root (PGDATA or the tablespace)
+ </para>
+ </listitem>
+ </itemizedlist>
+ </para>
</listitem>
</varlistentry>
</variablelist>
diff --git a/doc/src/sgml/ref/pg_basebackup.sgml
b/doc/src/sgml/ref/pg_basebackup.sgml
index 642fccf..a13b188 100644
*** a/doc/src/sgml/ref/pg_basebackup.sgml
--- b/doc/src/sgml/ref/pg_basebackup.sgml
*************** PostgreSQL documentation
*** 158,163 ****
--- 158,165 ----
tablespaces, the main data directory will be placed in the
target directory, but all other tablespaces will be placed
in the same absolute path as they have on the server.
+ The <filename>backup_profile</filename> file will be placed in
+ this directory.
</para>
<para>
This is the default format.
*************** PostgreSQL documentation
*** 174,186 ****
data directory will be written to a file named
<filename>base.tar</filename>, and all other tablespaces will
be named after the tablespace OID.
! </para>
<para>
If the value <literal>-</literal> (dash) is specified as
target directory, the tar contents will be written to
standard output, suitable for piping to for example
<productname>gzip</productname>. This is only possible if
the cluster has no additional tablespaces.
</para>
</listitem>
</varlistentry>
--- 176,192 ----
data directory will be written to a file named
<filename>base.tar</filename>, and all other tablespaces will
be named after the tablespace OID.
! The <filename>backup_profile</filename> file will be placed in
! this directory.
! </para>
<para>
If the value <literal>-</literal> (dash) is specified as
target directory, the tar contents will be written to
standard output, suitable for piping to for example
<productname>gzip</productname>. This is only possible if
the cluster has no additional tablespaces.
+ In this case, the <filename>backup_profile</filename> file
+ will be sent to standard output as part of the tar stream.
</para>
</listitem>
</varlistentry>
*************** PostgreSQL documentation
*** 189,194 ****
--- 195,214 ----
</varlistentry>
<varlistentry>
+ <term><option>-I <replaceable
class="parameter">directory</replaceable></option></term>
+ <term><option>--incremental=<replaceable
class="parameter">directory</replaceable></option></term>
+ <listitem>
+ <para>
+ Directory containing the backup to use as a start point for a
file-level
+ incremental backup. <application>pg_basebackup</application> will read
+ the <filename>backup_profile</filename> file and then create an
+ incremental backup containing only the files which have been modified
+ after the start point.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
<term><option>-r <replaceable
class="parameter">rate</replaceable></option></term>
<term><option>--max-rate=<replaceable
class="parameter">rate</replaceable></option></term>
<listitem>
*************** PostgreSQL documentation
*** 588,593 ****
--- 608,622 ----
</para>
<para>
+ In order to support file-level incremental backups, a
+ <filename>backup_profile</filename> file
+ is generated in the target directory as last step of every backup. This
+ file will be transparently used by <application>pg_basebackup</application>
+ when invoked with the option <replaceable>--incremental</replaceable> to
start
+ a new file-level incremental backup.
+ </para>
+
+ <para>
<application>pg_basebackup</application> works with servers of the same
or an older major version, down to 9.1. However, WAL streaming mode (-X
stream) only works with server version 9.3 and later.
diff --git a/src/backend/access/transam/xlog.c
b/src/backend/access/transam/xlog.c
index 629a457..a642a04 100644
*** a/src/backend/access/transam/xlog.c
--- b/src/backend/access/transam/xlog.c
***************
*** 47,52 ****
--- 47,53 ----
#include "replication/snapbuild.h"
#include "replication/walreceiver.h"
#include "replication/walsender.h"
+ #include "replication/basebackup.h"
#include "storage/barrier.h"
#include "storage/bufmgr.h"
#include "storage/fd.h"
*************** StartupXLOG(void)
*** 6164,6169 ****
--- 6165,6173 ----
* the latest recovery restartpoint instead of going all the
way back
* to the backup start point. It seems prudent though to just
rename
* the file out of the way rather than delete it completely.
+ *
+ * Rename also the backup profile if present. This marks the
data
+ * directory as not usable as base for an incremental backup.
*/
if (haveBackupLabel)
{
*************** StartupXLOG(void)
*** 6173,6178 ****
--- 6177,6189 ----
(errcode_for_file_access(),
errmsg("could not rename file
\"%s\" to \"%s\": %m",
BACKUP_LABEL_FILE, BACKUP_LABEL_OLD)));
+ unlink(BACKUP_PROFILE_OLD);
+ if (rename(BACKUP_PROFILE_FILE, BACKUP_PROFILE_OLD) != 0
+ && errno != ENOENT)
+ ereport(FATAL,
+ (errcode_for_file_access(),
+ errmsg("could not rename file
\"%s\" to \"%s\": %m",
+
BACKUP_PROFILE_FILE, BACKUP_PROFILE_OLD)));
}
/* Check that the GUCs used to generate the WAL allow recovery
*/
*************** XLogFileNameP(TimeLineID tli, XLogSegNo
*** 9249,9255 ****
* permissions of the calling user!
*/
XLogRecPtr
! do_pg_start_backup(const char *backupidstr, bool fast, TimeLineID *starttli_p,
char **labelfile)
{
bool exclusive = (labelfile == NULL);
--- 9260,9267 ----
* permissions of the calling user!
*/
XLogRecPtr
! do_pg_start_backup(const char *backupidstr, bool fast,
! XLogRecPtr incremental_startpoint,
TimeLineID *starttli_p,
char **labelfile)
{
bool exclusive = (labelfile == NULL);
*************** do_pg_start_backup(const char *backupids
*** 9468,9473 ****
--- 9480,9489 ----
(uint32) (startpoint >> 32), (uint32) startpoint,
xlogfilename);
appendStringInfo(&labelfbuf, "CHECKPOINT LOCATION: %X/%X\n",
(uint32) (checkpointloc >> 32),
(uint32) checkpointloc);
+ if (incremental_startpoint > 0)
+ appendStringInfo(&labelfbuf, "INCREMENTAL FROM
LOCATION: %X/%X\n",
+ (uint32)
(incremental_startpoint >> 32),
+ (uint32)
incremental_startpoint);
appendStringInfo(&labelfbuf, "BACKUP METHOD: %s\n",
exclusive ? "pg_start_backup"
: "streamed");
appendStringInfo(&labelfbuf, "BACKUP FROM: %s\n",
diff --git a/src/backend/access/transam/xlogfuncs.c
b/src/backend/access/transam/xlogfuncs.c
index 2179bf7..ace84d8 100644
*** a/src/backend/access/transam/xlogfuncs.c
--- b/src/backend/access/transam/xlogfuncs.c
*************** pg_start_backup(PG_FUNCTION_ARGS)
*** 59,65 ****
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser or replication role to run a
backup")));
! startpoint = do_pg_start_backup(backupidstr, fast, NULL, NULL);
PG_RETURN_LSN(startpoint);
}
--- 59,65 ----
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser or replication role to run a
backup")));
! startpoint = do_pg_start_backup(backupidstr, fast, 0, NULL, NULL);
PG_RETURN_LSN(startpoint);
}
diff --git a/src/backend/replication/basebackup.c
b/src/backend/replication/basebackup.c
index 3058ce9..107d70c 100644
*** a/src/backend/replication/basebackup.c
--- b/src/backend/replication/basebackup.c
***************
*** 30,40 ****
--- 30,42 ----
#include "replication/basebackup.h"
#include "replication/walsender.h"
#include "replication/walsender_private.h"
+ #include "storage/bufpage.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "utils/builtins.h"
#include "utils/elog.h"
#include "utils/ps_status.h"
+ #include "utils/pg_lsn.h"
#include "utils/timestamp.h"
*************** typedef struct
*** 46,56 ****
bool nowait;
bool includewal;
uint32 maxrate;
} basebackup_options;
! static int64 sendDir(char *path, int basepathlen, bool sizeonly, List
*tablespaces);
! static int64 sendTablespace(char *path, bool sizeonly);
static bool sendFile(char *readfilename, char *tarfilename,
struct stat * statbuf, bool missing_ok);
static void sendFileWithContent(const char *filename, const char *content);
--- 48,62 ----
bool nowait;
bool includewal;
uint32 maxrate;
+ XLogRecPtr incremental_startpoint;
} basebackup_options;
! static int64 sendDir(char *path, int basepathlen, bool sizeonly,
! List *tablespaces, bool has_relfiles,
! XLogRecPtr incremental_startpoint);
! static int64 sendTablespace(char *path, bool sizeonly,
! XLogRecPtr incremental_startpoint);
static bool sendFile(char *readfilename, char *tarfilename,
struct stat * statbuf, bool missing_ok);
static void sendFileWithContent(const char *filename, const char *content);
*************** static void parse_basebackup_options(Lis
*** 64,69 ****
--- 70,80 ----
static void SendXlogRecPtrResult(XLogRecPtr ptr, TimeLineID tli);
static int compareWalFileNames(const void *a, const void *b);
static void throttle(size_t increment);
+ static bool relnodeIsNewerThanLSN(char *filename, struct stat * statbuf,
+ XLogRecPtr *filemaxlsn, XLogRecPtr
thresholdlsn);
+ static void writeBackupProfileLine(const char *filename, struct stat *
statbuf,
+ bool
has_maxlsn, XLogRecPtr filemaxlsn, bool sent);
+ static void sendBackupProfile(const char *labelfile);
/* Was the backup currently in-progress initiated in recovery mode? */
static bool backup_started_in_recovery = false;
*************** static int64 elapsed_min_unit;
*** 93,98 ****
--- 104,115 ----
/* The last check of the transfer rate. */
static int64 throttled_last;
+ /* Temporary file containing the backup profile */
+ static File backup_profile_fd = 0;
+
+ /* Tablespace being currently sent. Used in backup profile generation */
+ static char *current_tablespace = NULL;
+
typedef struct
{
char *oid;
*************** perform_base_backup(basebackup_options *
*** 132,138 ****
backup_started_in_recovery = RecoveryInProgress();
! startptr = do_pg_start_backup(opt->label, opt->fastcheckpoint,
&starttli,
&labelfile);
/*
* Once do_pg_start_backup has been called, ensure that any failure
causes
--- 149,159 ----
backup_started_in_recovery = RecoveryInProgress();
! /* Open a temporary file to hold the profile content. */
! backup_profile_fd = OpenTemporaryFile(false);
!
! startptr = do_pg_start_backup(opt->label, opt->fastcheckpoint,
!
opt->incremental_startpoint, &starttli,
&labelfile);
/*
* Once do_pg_start_backup has been called, ensure that any failure
causes
*************** perform_base_backup(basebackup_options *
*** 208,214 ****
ti->oid = pstrdup(de->d_name);
ti->path = pstrdup(linkpath);
ti->rpath = relpath ? pstrdup(relpath) : NULL;
! ti->size = opt->progress ? sendTablespace(fullpath,
true) : -1;
tablespaces = lappend(tablespaces, ti);
#else
--- 229,236 ----
ti->oid = pstrdup(de->d_name);
ti->path = pstrdup(linkpath);
ti->rpath = relpath ? pstrdup(relpath) : NULL;
! ti->size = opt->progress ? sendTablespace(fullpath,
true,
!
opt->incremental_startpoint) : -1;
tablespaces = lappend(tablespaces, ti);
#else
*************** perform_base_backup(basebackup_options *
*** 225,231 ****
/* Add a node for the base directory at the end */
ti = palloc0(sizeof(tablespaceinfo));
! ti->size = opt->progress ? sendDir(".", 1, true, tablespaces) :
-1;
tablespaces = lappend(tablespaces, ti);
/* Send tablespace header */
--- 247,254 ----
/* Add a node for the base directory at the end */
ti = palloc0(sizeof(tablespaceinfo));
! ti->size = opt->progress ? sendDir(".", 1, true, tablespaces,
false,
!
opt->incremental_startpoint) : -1;
tablespaces = lappend(tablespaces, ti);
/* Send tablespace header */
*************** perform_base_backup(basebackup_options *
*** 267,272 ****
--- 290,301 ----
pq_sendint(&buf, 0, 2); /* natts */
pq_endmessage(&buf);
+ /*
+ * Save the current tablespace, used in
writeBackupProfileLine
+ * function
+ */
+ current_tablespace = ti->oid;
+
if (ti->path == NULL)
{
struct stat statbuf;
*************** perform_base_backup(basebackup_options *
*** 275,281 ****
sendFileWithContent(BACKUP_LABEL_FILE,
labelfile);
/* ... then the bulk of the files ... */
! sendDir(".", 1, false, tablespaces);
/* ... and pg_control after everything else. */
if (lstat(XLOG_CONTROL_FILE, &statbuf) != 0)
--- 304,310 ----
sendFileWithContent(BACKUP_LABEL_FILE,
labelfile);
/* ... then the bulk of the files ... */
! sendDir(".", 1, false, tablespaces, false,
opt->incremental_startpoint);
/* ... and pg_control after everything else. */
if (lstat(XLOG_CONTROL_FILE, &statbuf) != 0)
*************** perform_base_backup(basebackup_options *
*** 284,292 ****
errmsg("could not stat
control file \"%s\": %m",
XLOG_CONTROL_FILE)));
sendFile(XLOG_CONTROL_FILE, XLOG_CONTROL_FILE,
&statbuf, false);
}
else
! sendTablespace(ti->path, false);
/*
* If we're including WAL, and this is the main data
directory we
--- 313,322 ----
errmsg("could not stat
control file \"%s\": %m",
XLOG_CONTROL_FILE)));
sendFile(XLOG_CONTROL_FILE, XLOG_CONTROL_FILE,
&statbuf, false);
+ writeBackupProfileLine(XLOG_CONTROL_FILE,
&statbuf, false, 0, true);
}
else
! sendTablespace(ti->path, false,
opt->incremental_startpoint);
/*
* If we're including WAL, and this is the main data
directory we
*************** perform_base_backup(basebackup_options *
*** 501,507 ****
FreeFile(fp);
! /*
* Mark file as archived, otherwise files can get
archived again
* after promotion of a new node. This is in line with
* walreceiver.c always doing a XLogArchiveForceDone()
after a
--- 531,540 ----
FreeFile(fp);
! /* Add the WAL file to backup profile */
! writeBackupProfileLine(pathbuf, &statbuf, false, 0,
true);
!
! /*
* Mark file as archived, otherwise files can get
archived again
* after promotion of a new node. This is in line with
* walreceiver.c always doing a XLogArchiveForceDone()
after a
*************** perform_base_backup(basebackup_options *
*** 533,538 ****
--- 566,574 ----
sendFile(pathbuf, pathbuf, &statbuf, false);
+ /* Add the WAL file to backup profile */
+ writeBackupProfileLine(pathbuf, &statbuf, false, 0,
true);
+
/* unconditionally mark file as archived */
StatusFilePath(pathbuf, fname, ".done");
sendFileWithContent(pathbuf, "");
*************** perform_base_backup(basebackup_options *
*** 542,547 ****
--- 578,586 ----
pq_putemptymessage('c');
}
SendXlogRecPtrResult(endptr, endtli);
+
+ /* Send the profile file. */
+ sendBackupProfile(labelfile);
}
/*
*************** parse_basebackup_options(List *options,
*** 570,575 ****
--- 609,615 ----
bool o_nowait = false;
bool o_wal = false;
bool o_maxrate = false;
+ bool o_incremental = false;
MemSet(opt, 0, sizeof(*opt));
foreach(lopt, options)
*************** parse_basebackup_options(List *options,
*** 640,645 ****
--- 680,697 ----
opt->maxrate = (uint32) maxrate;
o_maxrate = true;
}
+ else if (strcmp(defel->defname, "incremental") == 0)
+ {
+ if (o_incremental)
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("duplicate option
\"%s\"", defel->defname)));
+
+ opt->incremental_startpoint = DatumGetLSN(
+ DirectFunctionCall1(pg_lsn_in,
+
CStringGetDatum(strVal(defel->arg))));
+ o_incremental = true;
+ }
else
elog(ERROR, "option \"%s\" not recognized",
defel->defname);
*************** sendFileWithContent(const char *filename
*** 859,864 ****
--- 911,919 ----
MemSet(buf, 0, pad);
pq_putmessage('d', buf, pad);
}
+
+ /* Write a backup profile entry for this file. */
+ writeBackupProfileLine(filename, &statbuf, false, 0, true);
}
/*
*************** sendFileWithContent(const char *filename
*** 869,875 ****
* Only used to send auxiliary tablespaces, not PGDATA.
*/
static int64
! sendTablespace(char *path, bool sizeonly)
{
int64 size;
char pathbuf[MAXPGPATH];
--- 924,930 ----
* Only used to send auxiliary tablespaces, not PGDATA.
*/
static int64
! sendTablespace(char *path, bool sizeonly, XLogRecPtr incremental_startpoint)
{
int64 size;
char pathbuf[MAXPGPATH];
*************** sendTablespace(char *path, bool sizeonly
*** 902,908 ****
size = 512; /* Size of the header
just added */
/* Send all the files in the tablespace version directory */
! size += sendDir(pathbuf, strlen(path), sizeonly, NIL);
return size;
}
--- 957,963 ----
size = 512; /* Size of the header
just added */
/* Send all the files in the tablespace version directory */
! size += sendDir(pathbuf, strlen(path), sizeonly, NIL, true,
incremental_startpoint);
return size;
}
*************** sendTablespace(char *path, bool sizeonly
*** 914,922 ****
*
* Omit any directory in the tablespaces list, to avoid backing up
* tablespaces twice when they were created inside PGDATA.
*/
static int64
! sendDir(char *path, int basepathlen, bool sizeonly, List *tablespaces)
{
DIR *dir;
struct dirent *de;
--- 969,981 ----
*
* Omit any directory in the tablespaces list, to avoid backing up
* tablespaces twice when they were created inside PGDATA.
+ *
+ * If 'has_relfiles' is set, this directory will be checked to identify
+ * relnode files and compute their maxLSN.
*/
static int64
! sendDir(char *path, int basepathlen, bool sizeonly, List *tablespaces,
! bool has_relfiles, XLogRecPtr incremental_startpoint)
{
DIR *dir;
struct dirent *de;
*************** sendDir(char *path, int basepathlen, boo
*** 1124,1138 ****
}
}
if (!skip_this_dir)
! size += sendDir(pathbuf, basepathlen, sizeonly,
tablespaces);
}
else if (S_ISREG(statbuf.st_mode))
{
bool sent = false;
if (!sizeonly)
! sent = sendFile(pathbuf, pathbuf + basepathlen
+ 1, &statbuf,
! true);
if (sent || sizeonly)
{
--- 1183,1243 ----
}
}
if (!skip_this_dir)
! {
! bool subdir_has_relfiles;
!
! /*
! * Whithin PGDATA relnode files are contained
only in "global"
! * and "base" directory
! */
! subdir_has_relfiles = has_relfiles
! || strcmp(pathbuf, "./global") == 0
! || strcmp(pathbuf, "./base") == 0;
!
! size += sendDir(pathbuf, basepathlen, sizeonly,
tablespaces,
!
subdir_has_relfiles, incremental_startpoint);
! }
}
else if (S_ISREG(statbuf.st_mode))
{
bool sent = false;
if (!sizeonly)
! {
! bool is_relfile;
! XLogRecPtr filemaxlsn = 0;
! int oidchars;
! ForkNumber forknum;
!
! /*
! * If the current directory can have relnode
files, check the file
! * name to see if it is one of them.
! *
! * Only copy the main fork because is the only
one
! * where page LSNs are always updated
! */
! is_relfile = ( has_relfiles
! &&
parse_filename_for_nontemp_relation(de->d_name,
!
&oidchars,
!
&forknum)
! && forknum == MAIN_FORKNUM);
!
! if (!is_relfile
! || incremental_startpoint == 0
! || relnodeIsNewerThanLSN(pathbuf,
&statbuf, &filemaxlsn,
!
incremental_startpoint))
! {
! sent = sendFile(pathbuf, pathbuf +
basepathlen + 1,
!
&statbuf, true);
! /* Write a backup profile entry for the
sent file. */
! writeBackupProfileLine(pathbuf +
basepathlen + 1, &statbuf,
!
false, 0, sent);
! }
! else
! /* Write a backup profile entry for the
skipped file. */
! writeBackupProfileLine(pathbuf +
basepathlen + 1, &statbuf,
!
true, filemaxlsn, sent);
! }
if (sent || sizeonly)
{
*************** throttle(size_t increment)
*** 1333,1335 ****
--- 1438,1626 ----
/* Sleep was necessary but might have been interrupted. */
throttled_last = GetCurrentIntegerTimestamp();
}
+
+ /*
+ * Search in a relnode file for a page with a LSN greater than the threshold.
+ * If all the blocks in the file are older than the threshold the file can
+ * be safely skipped during an incremental backup.
+ */
+ static bool
+ relnodeIsNewerThanLSN(char *filename, struct stat * statbuf,
+ XLogRecPtr *filemaxlsn, XLogRecPtr thresholdlsn)
+ {
+ FILE *fp;
+ char buf[BLCKSZ];
+ size_t cnt;
+ pgoff_t len = 0;
+ XLogRecPtr pagelsn;
+
+ *filemaxlsn = 0;
+
+ fp = AllocateFile(filename, "rb");
+ if (fp == NULL)
+ {
+ if (errno == ENOENT)
+ return true;
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not open file \"%s\": %m",
filename)));
+ }
+
+ while ((cnt = fread(buf, 1, Min(sizeof(buf), statbuf->st_size - len),
fp)) > 0)
+ {
+ pagelsn = PageGetLSN(buf);
+
+ /* Keep the max LSN found */
+ if (*filemaxlsn < pagelsn)
+ *filemaxlsn = pagelsn;
+
+ /*
+ * If a page with a LSN newer than the threshold stop scanning
+ * and set the filemaxlsn value to 0 as it is only partial.
+ */
+ if (thresholdlsn <= pagelsn)
+ {
+ *filemaxlsn = 0;
+ FreeFile(fp);
+ return true;
+ }
+
+ if (len >= statbuf->st_size)
+ {
+ /*
+ * Reached end of file. The file could be longer, if it
was
+ * extended while we were sending it, but for a base
backup we can
+ * ignore such extended data. It will be restored from
WAL.
+ */
+ break;
+ }
+ }
+
+ FreeFile(fp);
+
+ /*
+ * At this point, if *filemaxlsn contains InvalidXLogRecPtr
+ * the file contains something that doesn't update page LSNs (e.g. FSM)
+ */
+ if (*filemaxlsn == InvalidXLogRecPtr)
+ return true;
+
+ return false;
+ }
+
+ /*
+ * Write an entry in file list section of backup profile.
+ */
+ static void
+ writeBackupProfileLine(const char *filename, struct stat * statbuf,
+ bool has_maxlsn, XLogRecPtr
filemaxlsn, bool sent)
+ {
+ /*
+ * tablespace oid (10) + max LSN (17) + mtime (10) + size (19) +
+ * path (MAXPGPATH) + separators (4) + trailing \0 = 65
+ */
+ char buf[MAXPGPATH + 65];
+ char maxlsn[17];
+ int rowlen;
+
+ Assert(backup_profile_fd > 0);
+
+ /* Prepare maxlsn */
+ if (has_maxlsn)
+ {
+ snprintf(maxlsn, sizeof(maxlsn), "%X/%X",
+ (uint32) (filemaxlsn >> 32), (uint32)
filemaxlsn);
+ }
+ else
+ {
+ strlcpy(maxlsn, "\\N", sizeof(maxlsn));
+ }
+
+ rowlen = snprintf(buf, sizeof(buf), "%s\t%s\t%s\t%u\t%lld\t%s\n",
+ current_tablespace ?
current_tablespace : "\\N",
+ maxlsn,
+ sent ? "t" : "f",
+ (uint32) statbuf->st_mtime,
+ statbuf->st_size,
+ filename);
+ FileWrite(backup_profile_fd, buf, rowlen);
+ }
+
+ /*
+ * Send the backup profile. It is wrapped in a tar CopyOutResponse containing
+ * a tar stream with only one file.
+ */
+ static void
+ sendBackupProfile(const char *labelfile)
+ {
+ StringInfoData msgbuf;
+ struct stat statbuf;
+ char buf[TAR_SEND_SIZE];
+ size_t cnt;
+ pgoff_t len = 0;
+ size_t pad;
+ char *backup_profile = FilePathName(backup_profile_fd);
+
+ /* Send CopyOutResponse message */
+ pq_beginmessage(&msgbuf, 'H');
+ pq_sendbyte(&msgbuf, 0); /* overall format */
+ pq_sendint(&msgbuf, 0, 2); /* natts */
+ pq_endmessage(&msgbuf);
+
+ if (lstat(backup_profile, &statbuf) != 0)
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not stat backup_profile file
\"%s\": %m",
+ backup_profile)));
+
+ /* Set the file position to the beginning. */
+ FileSeek(backup_profile_fd, 0, SEEK_SET);
+
+ /*
+ * Fill the buffer with content of backup profile header section. Being
it
+ * the concatenation of two separator and the backup label, it should be
+ * shorter of TAR_SEND_SIZE.
+ */
+ cnt = snprintf(buf, sizeof(buf), "%s\n%s%s\n",
+ BACKUP_PROFILE_HEADER,
+ labelfile,
+ BACKUP_PROFILE_SEPARATOR);
+
+ /* Add size of backup label and separators */
+ statbuf.st_size += cnt;
+
+ _tarWriteHeader(BACKUP_PROFILE_FILE, NULL, &statbuf);
+
+ /* Send backup profile header */
+ if (pq_putmessage('d', buf, cnt))
+ ereport(ERROR,
+ (errmsg("base backup could not send data,
aborting backup")));
+
+ len += cnt;
+ throttle(cnt);
+
+ while ((cnt = FileRead(backup_profile_fd, buf, sizeof(buf))) > 0)
+ {
+ /* Send the chunk as a CopyData message */
+ if (pq_putmessage('d', buf, cnt))
+ ereport(ERROR,
+ (errmsg("base backup could not send
data, aborting backup")));
+
+ len += cnt;
+ throttle(cnt);
+
+ }
+
+ /*
+ * Pad to 512 byte boundary, per tar format requirements. (This small
+ * piece of data is probably not worth throttling.)
+ */
+ pad = ((len + 511) & ~511) - len;
+ if (pad > 0)
+ {
+ MemSet(buf, 0, pad);
+ pq_putmessage('d', buf, pad);
+ }
+
+ pq_putemptymessage('c'); /* CopyDone */
+ }
diff --git a/src/backend/replication/repl_gram.y
b/src/backend/replication/repl_gram.y
index 2a41eb1..684cf4d 100644
*** a/src/backend/replication/repl_gram.y
--- b/src/backend/replication/repl_gram.y
*************** Node *replication_parse_result;
*** 75,80 ****
--- 75,81 ----
%token K_PHYSICAL
%token K_LOGICAL
%token K_SLOT
+ %token K_INCREMENTAL
%type <node> command
%type <node> base_backup start_replication start_logical_replication
create_replication_slot drop_replication_slot identify_system timeline_history
*************** base_backup_opt:
*** 168,173 ****
--- 169,179 ----
$$ = makeDefElem("max_rate",
(Node
*)makeInteger($2));
}
+ | K_INCREMENTAL SCONST
+ {
+ $$ = makeDefElem("incremental",
+ (Node
*)makeString($2));
+ }
;
create_replication_slot:
diff --git a/src/backend/replication/repl_scanner.l
b/src/backend/replication/repl_scanner.l
index 449c127..a6d0dd8 100644
*** a/src/backend/replication/repl_scanner.l
--- b/src/backend/replication/repl_scanner.l
*************** TIMELINE_HISTORY { return K_TIMELINE_HIS
*** 96,101 ****
--- 96,102 ----
PHYSICAL { return K_PHYSICAL; }
LOGICAL { return K_LOGICAL; }
SLOT { return K_SLOT; }
+ INCREMENTAL { return K_INCREMENTAL; }
"," { return ','; }
";" { return ';'; }
diff --git a/src/bin/pg_basebackup/pg_basebackup.c
b/src/bin/pg_basebackup/pg_basebackup.c
index fbf7106..fd67d51 100644
*** a/src/bin/pg_basebackup/pg_basebackup.c
--- b/src/bin/pg_basebackup/pg_basebackup.c
*************** static bool writerecoveryconf = false;
*** 67,72 ****
--- 67,74 ----
static int standby_message_timeout = 10 * 1000; /* 10 sec =
default */
static pg_time_t last_progress_report = 0;
static int32 maxrate = 0; /* no limit by default */
+ static XLogRecPtr incremental_startpoint = 0;
+ static TimeLineID incremental_timeline = 0;
/* Progress counters */
*************** static void usage(void);
*** 99,107 ****
static void disconnect_and_exit(int code);
static void verify_dir_is_empty_or_create(char *dirname);
static void progress_report(int tablespacenum, const char *filename, bool
force);
static void ReceiveTarFile(PGconn *conn, PGresult *res, int rownum);
! static void ReceiveAndUnpackTarFile(PGconn *conn, PGresult *res, int rownum);
static void GenerateRecoveryConf(PGconn *conn);
static void WriteRecoveryConf(void);
static void BaseBackup(void);
--- 101,111 ----
static void disconnect_and_exit(int code);
static void verify_dir_is_empty_or_create(char *dirname);
static void progress_report(int tablespacenum, const char *filename, bool
force);
+ static void read_backup_profile_header(const char *profile_path);
static void ReceiveTarFile(PGconn *conn, PGresult *res, int rownum);
! static void ReceiveAndUnpackTarFile(PGconn *conn, PGresult *res, int rownum,
! const
char *dest_path);
static void GenerateRecoveryConf(PGconn *conn);
static void WriteRecoveryConf(void);
static void BaseBackup(void);
*************** usage(void)
*** 232,237 ****
--- 236,243 ----
printf(_("\nOptions controlling the output:\n"));
printf(_(" -D, --pgdata=DIRECTORY receive base backup into
directory\n"));
printf(_(" -F, --format=p|t output format (plain (default),
tar)\n"));
+ printf(_(" -I, --incremental=DIRECTORY\n"
+ " incremental backup from an
existing backup\n"));
printf(_(" -r, --max-rate=RATE maximum transfer rate to transfer
data directory\n"
" (in kB/s, or use suffix
\"k\" or \"M\")\n"));
printf(_(" -R, --write-recovery-conf\n"
*************** parse_max_rate(char *src)
*** 717,722 ****
--- 723,794 ----
return (int32) result;
}
+
+ /*
+ * Read incremental_startpoint and incremental_timeline
+ * from a backup profile.
+ */
+ static void
+ read_backup_profile_header(const char *reference_path)
+ {
+ char profile_path[MAXPGPATH];
+ FILE *pfp;
+ char ch;
+ uint32 hi,
+ lo;
+
+ /* The directory must exist and must be not empty */
+ if (pg_check_dir(reference_path) < 3)
+ {
+ fprintf(stderr, _("%s: invalid incremental base directory
\"%s\"\n"),
+ progname, reference_path);
+ exit(1);
+ }
+
+ /* Build the backup profile location */
+ join_path_components(profile_path, reference_path, BACKUP_PROFILE_FILE);
+
+ /* See if label file is present */
+ pfp = fopen(profile_path, "r");
+ if (!pfp)
+ {
+ fprintf(stderr, _("%s: could not read file \"%s\": %s\n"),
+ progname, profile_path, strerror(errno));
+ exit(1);
+ }
+
+ /* Consume the profile header */
+ fscanf(pfp, BACKUP_PROFILE_HEADER);
+ if (fscanf(pfp, "%c", &ch) != 1 || ch != '\n')
+ {
+ fprintf(stderr, _("%s: invalid data in file \"%s\"\n"),
+ progname, profile_path);
+ exit(1);
+ }
+
+ /*
+ * Read and parse the START WAL LOCATION (this code
+ * is pretty crude, but we are not expecting any variability in the file
+ * format).
+ */
+ if (fscanf(pfp, "START WAL LOCATION: %X/%X (file %08X%*16s)%c",
+ &hi, &lo, &incremental_timeline, &ch) != 4 || ch !=
'\n')
+ {
+ fprintf(stderr, _("%s: invalid data in file \"%s\"\n"),
+ progname, profile_path);
+ exit(1);
+ }
+ incremental_startpoint = ((uint64) hi) << 32 | lo;
+
+ if (ferror(pfp) || fclose(pfp))
+ {
+ fprintf(stderr, _("%s: could not read file \"%s\": %s\n"),
+ progname, profile_path, strerror(errno));
+ exit(1);
+ }
+ }
+
+
/*
* Write a piece of tar data
*/
*************** ReceiveTarFile(PGconn *conn, PGresult *r
*** 773,784 ****
char *copybuf = NULL;
FILE *tarfile = NULL;
char tarhdr[512];
! bool basetablespace = PQgetisnull(res, rownum, 0);
bool in_tarhdr = true;
bool skip_file = false;
size_t tarhdrsz = 0;
size_t filesz = 0;
#ifdef HAVE_LIBZ
gzFile ztarfile = NULL;
#endif
--- 845,866 ----
char *copybuf = NULL;
FILE *tarfile = NULL;
char tarhdr[512];
! bool basetablespace;
bool in_tarhdr = true;
bool skip_file = false;
size_t tarhdrsz = 0;
size_t filesz = 0;
+ /*
+ * If 'res' is NULL, we are appending the backup profile to
+ * the standard output tar stream.
+ */
+ assert(res || (strcmp(basedir, "-") == 0));
+ if (res)
+ basetablespace = PQgetisnull(res, rownum, 0);
+ else
+ basetablespace = true;
+
#ifdef HAVE_LIBZ
gzFile ztarfile = NULL;
#endif
*************** ReceiveTarFile(PGconn *conn, PGresult *r
*** 939,946 ****
WRITE_TAR_DATA(zerobuf, padding);
}
! /* 2 * 512 bytes empty data at end of file */
! WRITE_TAR_DATA(zerobuf, sizeof(zerobuf));
#ifdef HAVE_LIBZ
if (ztarfile != NULL)
--- 1021,1033 ----
WRITE_TAR_DATA(zerobuf, padding);
}
! /*
! * Write the end-of-file blocks unless using stdout
! * and not writing the backup profile (res is NULL).
! */
! if (!res || strcmp(basedir, "-") != 0)
! /* 2 * 512 bytes empty data at end of file */
! WRITE_TAR_DATA(zerobuf, sizeof(zerobuf));
#ifdef HAVE_LIBZ
if (ztarfile != NULL)
*************** get_tablespace_mapping(const char *dir)
*** 1128,1136 ****
* If the data is for the main data directory, it will be restored in the
* specified directory. If it's for another tablespace, it will be restored
* in the original or mapped directory.
*/
static void
! ReceiveAndUnpackTarFile(PGconn *conn, PGresult *res, int rownum)
{
char current_path[MAXPGPATH];
char filename[MAXPGPATH];
--- 1215,1230 ----
* If the data is for the main data directory, it will be restored in the
* specified directory. If it's for another tablespace, it will be restored
* in the original or mapped directory.
+ *
+ * If 'res' is NULL, the destination directory is taken from the
+ * 'dest_path' parameter.
+ *
+ * When 'dest_path' is specified, progresses are not displayed because the
+ * content it is not in any tablespace.
*/
static void
! ReceiveAndUnpackTarFile(PGconn *conn, PGresult *res, int rownum,
! const char *dest_path)
{
char current_path[MAXPGPATH];
char filename[MAXPGPATH];
*************** ReceiveAndUnpackTarFile(PGconn *conn, PG
*** 1141,1153 ****
char *copybuf = NULL;
FILE *file = NULL;
! basetablespace = PQgetisnull(res, rownum, 0);
! if (basetablespace)
! strlcpy(current_path, basedir, sizeof(current_path));
else
! strlcpy(current_path,
! get_tablespace_mapping(PQgetvalue(res, rownum,
1)),
! sizeof(current_path));
/*
* Get the COPY data
--- 1235,1262 ----
char *copybuf = NULL;
FILE *file = NULL;
! /* 'res' and 'dest_path' are mutually exclusive */
! assert(!res != !dest_path);
!
! /*
! * If 'res' is NULL, the destination directory is taken from the
! * 'dest_path' parameter.
! */
! if (res)
! {
! basetablespace = PQgetisnull(res, rownum, 0);
! if (basetablespace)
! strlcpy(current_path, basedir, sizeof(current_path));
! else
! strlcpy(current_path,
! get_tablespace_mapping(PQgetvalue(res,
rownum, 1)),
! sizeof(current_path));
! }
else
! {
! basetablespace = false;
! strlcpy(current_path, dest_path, sizeof(current_path));
! }
/*
* Get the COPY data
*************** ReceiveAndUnpackTarFile(PGconn *conn, PG
*** 1355,1361 ****
disconnect_and_exit(1);
}
totaldone += r;
! progress_report(rownum, filename, false);
current_len_left -= r;
if (current_len_left == 0 && current_padding == 0)
--- 1464,1472 ----
disconnect_and_exit(1);
}
totaldone += r;
! /* report progress unless a custom destination is used
*/
! if (!dest_path)
! progress_report(rownum, filename, false);
current_len_left -= r;
if (current_len_left == 0 && current_padding == 0)
*************** ReceiveAndUnpackTarFile(PGconn *conn, PG
*** 1371,1377 ****
}
} /* continuing
data in existing file */
} /* loop over
all data blocks */
! progress_report(rownum, filename, true);
if (file != NULL)
{
--- 1482,1490 ----
}
} /* continuing
data in existing file */
} /* loop over
all data blocks */
! /* report progress unless a custom destination is used */
! if (!dest_path)
! progress_report(rownum, filename, true);
if (file != NULL)
{
*************** BaseBackup(void)
*** 1587,1592 ****
--- 1700,1706 ----
char *basebkp;
char escaped_label[MAXPGPATH];
char *maxrate_clause = NULL;
+ char *incremental_clause = NULL;
int i;
char xlogstart[64];
char xlogend[64];
*************** BaseBackup(void)
*** 1648,1661 ****
if (maxrate > 0)
maxrate_clause = psprintf("MAX_RATE %u", maxrate);
basebkp =
! psprintf("BASE_BACKUP LABEL '%s' %s %s %s %s %s",
escaped_label,
showprogress ? "PROGRESS" : "",
includewal && !streamwal ? "WAL" : "",
fastcheckpoint ? "FAST" : "",
includewal ? "NOWAIT" : "",
! maxrate_clause ? maxrate_clause : "");
if (PQsendQuery(conn, basebkp) == 0)
{
--- 1762,1801 ----
if (maxrate > 0)
maxrate_clause = psprintf("MAX_RATE %u", maxrate);
+ if (incremental_startpoint > 0)
+ {
+ incremental_clause = psprintf("INCREMENTAL '%X/%X'",
+
(uint32) (incremental_startpoint >> 32),
+
(uint32) incremental_startpoint);
+
+ /*
+ * Sanity check: if from a different timeline abort the backup.
+ */
+ if (latesttli != incremental_timeline)
+ {
+ fprintf(stderr,
+ _("%s: incremental backup from a
different timeline "
+ "is not supported: base=%u
current=%u\n"),
+ progname, incremental_timeline,
latesttli);
+ disconnect_and_exit(1);
+ }
+
+ if (verbose)
+ fprintf(stderr, _("incremental from point: %X/%X on
timeline %u\n"),
+ (uint32) (incremental_startpoint >> 32),
+ (uint32) incremental_startpoint,
+ incremental_timeline);
+ }
+
basebkp =
! psprintf("BASE_BACKUP LABEL '%s' %s %s %s %s %s %s",
escaped_label,
showprogress ? "PROGRESS" : "",
includewal && !streamwal ? "WAL" : "",
fastcheckpoint ? "FAST" : "",
includewal ? "NOWAIT" : "",
! maxrate_clause ? maxrate_clause : "",
! incremental_clause ? incremental_clause : "");
if (PQsendQuery(conn, basebkp) == 0)
{
*************** BaseBackup(void)
*** 1769,1775 ****
if (format == 't')
ReceiveTarFile(conn, res, i);
else
! ReceiveAndUnpackTarFile(conn, res, i);
} /* Loop over
all tablespaces */
if (showprogress)
--- 1909,1915 ----
if (format == 't')
ReceiveTarFile(conn, res, i);
else
! ReceiveAndUnpackTarFile(conn, res, i, NULL);
} /* Loop over
all tablespaces */
if (showprogress)
*************** BaseBackup(void)
*** 1803,1808 ****
--- 1943,1960 ----
fprintf(stderr, "transaction log end point: %s\n", xlogend);
PQclear(res);
+ /*
+ * Get the backup profile
+ *
+ * If format is tar and we are writing on standard output
+ * append the backup profile to the stream, otherwise put it
+ * in the destination directory
+ */
+ if (format == 't' && (strcmp(basedir, "-") == 0))
+ ReceiveTarFile(conn, NULL, -1);
+ else
+ ReceiveAndUnpackTarFile(conn, NULL, -1, basedir);
+
res = PQgetResult(conn);
if (PQresultStatus(res) != PGRES_COMMAND_OK)
{
*************** main(int argc, char **argv)
*** 1942,1947 ****
--- 2094,2100 ----
{"username", required_argument, NULL, 'U'},
{"no-password", no_argument, NULL, 'w'},
{"password", no_argument, NULL, 'W'},
+ {"incremental", required_argument, NULL, 'I'},
{"status-interval", required_argument, NULL, 's'},
{"verbose", no_argument, NULL, 'v'},
{"progress", no_argument, NULL, 'P'},
*************** main(int argc, char **argv)
*** 1949,1955 ****
{NULL, 0, NULL, 0}
};
int c;
-
int option_index;
progname = get_progname(argv[0]);
--- 2102,2107 ----
*************** main(int argc, char **argv)
*** 1970,1976 ****
}
}
! while ((c = getopt_long(argc, argv, "D:F:r:RT:xX:l:zZ:d:c:h:p:U:s:wWvP",
long_options,
&option_index)) != -1)
{
switch (c)
--- 2122,2128 ----
}
}
! while ((c = getopt_long(argc, argv,
"D:F:r:RT:xX:l:zZ:d:c:h:p:U:s:wWI:vP",
long_options,
&option_index)) != -1)
{
switch (c)
*************** main(int argc, char **argv)
*** 2088,2093 ****
--- 2240,2248 ----
case 'W':
dbgetpassword = 1;
break;
+ case 'I':
+ read_backup_profile_header(optarg);
+ break;
case 's':
standby_message_timeout = atoi(optarg) * 1000;
if (standby_message_timeout < 0)
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 138deaf..4bb261a 100644
*** a/src/include/access/xlog.h
--- b/src/include/access/xlog.h
*************** extern void SetWalWriterSleeping(bool sl
*** 249,255 ****
* Starting/stopping a base backup
*/
extern XLogRecPtr do_pg_start_backup(const char *backupidstr, bool fast,
! TimeLineID *starttli_p, char **labelfile);
extern XLogRecPtr do_pg_stop_backup(char *labelfile, bool waitforarchive,
TimeLineID *stoptli_p);
extern void do_pg_abort_backup(void);
--- 249,256 ----
* Starting/stopping a base backup
*/
extern XLogRecPtr do_pg_start_backup(const char *backupidstr, bool fast,
! XLogRecPtr incremental_startpoint,
! TimeLineID *starttli_p, char **labelfile);
extern XLogRecPtr do_pg_stop_backup(char *labelfile, bool waitforarchive,
TimeLineID *stoptli_p);
extern void do_pg_abort_backup(void);
diff --git a/src/include/replication/basebackup.h
b/src/include/replication/basebackup.h
index 64f2bd5..08f8e90 100644
*** a/src/include/replication/basebackup.h
--- b/src/include/replication/basebackup.h
***************
*** 20,25 ****
--- 20,30 ----
#define MAX_RATE_LOWER 32
#define MAX_RATE_UPPER 1048576
+ /* Backup profile */
+ #define BACKUP_PROFILE_HEADER "POSTGRESQL BACKUP PROFILE 1"
+ #define BACKUP_PROFILE_SEPARATOR "FILE LIST"
+ #define BACKUP_PROFILE_FILE "backup_profile"
+ #define BACKUP_PROFILE_OLD "backup_profile.old"
extern void SendBaseBackup(BaseBackupCmd *cmd);
--
2.2.2
signature.asc
Description: OpenPGP digital signature
