Add file_extend_method=posix_fallocate,write_zeros.

Provide a way to disable the use of posix_fallocate() for relation
files.  It was introduced by commit 4d330a61bb1.  The new setting
file_extend_method=write_zeros can be used as a workaround for problems
reported from the field:

 * BTRFS compression is disabled by the use of posix_fallocate()
 * XFS could produce spurious ENOSPC errors in some Linux kernel
   versions, though that problem is reported to have been fixed

The default is file_extend_method=posix_fallocate if available, as
before.  The write_zeros option is similar to PostgreSQL < 16, except
that now it's multi-block.

Backpatch-through: 16
Reviewed-by: Jakub Wartak <jakub.wartak@enterprisedb.com>
Reported-by: Dimitrios Apostolou <jimis@gmx.net>
Discussion: https://postgr.es/m/b1843124-fd22-e279-a31f-252dffb6fbf2%40gmx.net

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index d0dc5bac43974e552f45ba57af1eb18175f4319d..f675523e8c8699cedb686fa3d3af00b47246a82a 100644 (file)
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -2210,6 +2210,42 @@ include_dir 'conf.d'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-file-extend-method" xreflabel="file_extend_method">
+      <term><varname>file_extend_method</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>file_extend_method</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the method used to extend data files during bulk operations
+        such as <command>COPY</command>.  The first available option is used as
+        the default, depending on the operating system:
+        <itemizedlist>
+         <listitem>
+          <para>
+           <literal>posix_fallocate</literal> (Unix) uses the standard POSIX
+            interface for allocating disk space, but is missing on some systems.
+            If it is present but the underlying file system doesn't support it,
+            this option silently falls back to <literal>write_zeros</literal>.
+            Current versions of BTRFS are known to disable compression when
+            this option is used.
+            This is the default on systems that have the function.
+           </para>
+         </listitem>
+         <listitem>
+          <para>
+           <literal>write_zeros</literal> extends files by writing out blocks
+            of zero bytes.  This is the default on systems that don't have the
+            function <function>posix_fallocate</function>.
+          </para>
+         </listitem>
+        </itemizedlist>
+        The <literal>write_zeros</literal> method is always used when data
+        files are extended by 8 blocks or fewer.
+       </para>
+      </listitem>
+     </varlistentry>
      </variablelist>
      </sect2>
 

diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index ee91bb79aca394ba0e45d34e43e492f7f07cb76c..b54c42d9f84991c2ce4aa0aae4461c91b8c05aab 100644 (file)
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -164,6 +164,9 @@ bool                data_sync_retry = false;
 /* How SyncDataDirectory() should do its job. */
 int                    recovery_init_sync_method = RECOVERY_INIT_SYNC_METHOD_FSYNC;
 
+/* How data files should be bulk-extended with zeros. */
+int                    file_extend_method = DEFAULT_FILE_EXTEND_METHOD;
+
 /* Which kinds of files should be opened with PG_O_DIRECT. */
 int                    io_direct_flags;
 

diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 47c01ed72711151d0879781a246f917bc79d899b..e6f1ad21fe8186ae2fb93c5be079a39addb76030 100644 (file)
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -577,13 +577,24 @@ mdzeroextend(SMgrRelation reln, ForkNumber forknum,
                 * that decision should be made though? For now just use a cutoff of
                 * 8, anything between 4 and 8 worked OK in some local testing.
                 */
-               if (numblocks > 8)
+               if (numblocks > 8 &&
+                       file_extend_method != FILE_EXTEND_METHOD_WRITE_ZEROS)
                {
-                       int                     ret;
+                       int                     ret = 0;
 
-                       ret = FileFallocate(v->mdfd_vfd,
-                                                               seekpos, (off_t) BLCKSZ * numblocks,
-                                                               WAIT_EVENT_DATA_FILE_EXTEND);
+#ifdef HAVE_POSIX_FALLOCATE
+                       if (file_extend_method == FILE_EXTEND_METHOD_POSIX_FALLOCATE)
+                       {
+                               ret = FileFallocate(v->mdfd_vfd,
+                                                                       seekpos, (off_t) BLCKSZ * numblocks,
+                                                                       WAIT_EVENT_DATA_FILE_EXTEND);
+                       }
+                       else
+#endif
+                       {
+                               elog(ERROR, "unsupported file_extend_method: %d",
+                                        file_extend_method);
+                       }
                        if (ret != 0)
                        {
                                ereport(ERROR,

diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index ab97dea63c448e1a1d129dc4227a450f042d8829..093567535bdff5c444ef35a23bb2d1a67e96281a 100644 (file)
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -66,6 +66,7 @@
 #include "replication/slot.h"
 #include "replication/syncrep.h"
 #include "storage/bufmgr.h"
+#include "storage/fd.h"
 #include "storage/large_object.h"
 #include "storage/pg_shmem.h"
 #include "storage/predicate.h"
@@ -470,6 +471,14 @@ static const struct config_enum_entry wal_compression_options[] = {
        {NULL, 0, false}
 };
 
+static const struct config_enum_entry file_extend_method_options[] = {
+#ifdef HAVE_POSIX_FALLOCATE
+       {"posix_fallocate", FILE_EXTEND_METHOD_POSIX_FALLOCATE, false},
+#endif
+       {"write_zeros", FILE_EXTEND_METHOD_WRITE_ZEROS, false},
+       {NULL, 0, false}
+};
+
 /*
  * Options for enum values stored in other modules
  */
@@ -4847,6 +4856,16 @@ struct config_enum ConfigureNamesEnum[] =
                NULL, NULL, NULL
        },
 
+       {
+               {"file_extend_method", PGC_SIGHUP, RESOURCES_DISK,
+                       gettext_noop("Selects the method used for extending data files."),
+                       NULL
+               },
+               &file_extend_method,
+               DEFAULT_FILE_EXTEND_METHOD, file_extend_method_options,
+               NULL, NULL, NULL
+       },
+
        {
                {"wal_sync_method", PGC_SIGHUP, WAL_SETTINGS,
                        gettext_noop("Selects the method used for forcing WAL updates to disk."),

diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index de0ed211f383674ec3154d0b8ab001c38af14de3..c8ffcdf7b169ddea63f993482b2dc223824ed611 100644 (file)
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -167,6 +167,11 @@
 #temp_file_limit = -1                  # limits per-process temp file space
                                        # in kilobytes, or -1 for no limit
 
+#file_extend_method = posix_fallocate   # the default is the first option supported
+                                       # by the operating system:
+                                       #   posix_fallocate (most Unix-like systems)
+                                       #   write_zeros
+
 # - Kernel Resources -
 
 #max_files_per_process = 1000          # min 64

diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
index 6791a406fc11441857ba8168d2f3e52b9292f35a..26809899591515cfd80ab887a864fa7a600caf27 100644 (file)
--- a/src/include/storage/fd.h
+++ b/src/include/storage/fd.h
@@ -59,12 +59,23 @@ typedef int File;
 #define IO_DIRECT_WAL                  0x02
 #define IO_DIRECT_WAL_INIT             0x04
 
+enum FileExtendMethod
+{
+#ifdef HAVE_POSIX_FALLOCATE
+       FILE_EXTEND_METHOD_POSIX_FALLOCATE,
+#endif
+       FILE_EXTEND_METHOD_WRITE_ZEROS,
+};
+
+/* Default to the first available file_extend_method. */
+#define DEFAULT_FILE_EXTEND_METHOD 0
 
 /* GUC parameter */
 extern PGDLLIMPORT int max_files_per_process;
 extern PGDLLIMPORT bool data_sync_retry;
 extern PGDLLIMPORT int recovery_init_sync_method;
 extern PGDLLIMPORT int io_direct_flags;
+extern PGDLLIMPORT int file_extend_method;
 
 /*
  * This is private to fd.c, but exported for save/restore_backend_variables()