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 0cacc062cddd7bba3b141e31f764fea11dfe70cd..f1af1505cf321503b0682335b913dcf5cde7e190 100644 (file)
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -2412,6 +2412,43 @@ 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>
+
      <varlistentry id="guc-max-notify-queue-pages" xreflabel="max_notify_queue_pages">
       <term><varname>max_notify_queue_pages</varname> (<type>integer</type>)
       <indexterm>

diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index 0f8083651dec351dcbe01fe15e38ddbeefb35793..5d07b64a1ef396bfbc3cea5557712465e1ed3394 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 = DATA_DIR_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 a262587118553dc72c300956206886127cbd4689..443434e4ea86e0192618d3f84cfd48f439c0485b 100644 (file)
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -602,13 +602,24 @@ 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, (pgoff_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, (pgoff_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_parameters.dat b/src/backend/utils/misc/guc_parameters.dat
index f0260e6e412cea5c188eb3e22d5a6414921a5eff..c1f1603cd39d93815c5a8b78081fb8f6d91ef36c 100644 (file)
--- a/src/backend/utils/misc/guc_parameters.dat
+++ b/src/backend/utils/misc/guc_parameters.dat
@@ -1042,6 +1042,13 @@
   options => 'file_copy_method_options',
 },
 
+{ name => 'file_extend_method', type => 'enum', context => 'PGC_SIGHUP', group => 'RESOURCES_DISK',
+  short_desc => 'Selects the method used for extending data files.',
+  variable => 'file_extend_method',
+  boot_val => 'DEFAULT_FILE_EXTEND_METHOD',
+  options => 'file_extend_method_options',
+},
+
 { name => 'from_collapse_limit', type => 'int', context => 'PGC_USERSET', group => 'QUERY_TUNING_OTHER',
   short_desc => 'Sets the FROM-list size beyond which subqueries are not collapsed.',
   long_desc => 'The planner will merge subqueries into upper queries if the resulting FROM list would have no more than this many items.',

diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index 13c569d8790eb86b43d0575d9de821df0583e9c5..5df3a36bf6429bb8f55bc30e613ffc40e0b69a87 100644 (file)
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -80,6 +80,7 @@
 #include "storage/bufmgr.h"
 #include "storage/bufpage.h"
 #include "storage/copydir.h"
+#include "storage/fd.h"
 #include "storage/io_worker.h"
 #include "storage/large_object.h"
 #include "storage/pg_shmem.h"
@@ -491,6 +492,14 @@ static const struct config_enum_entry file_copy_method_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
  */

diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index c4f92fcdac88d1db09e02aeb08a486a4188d6a8c..1ae594af84310e7c46845401dffebdd1ea1d0ddf 100644 (file)
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -179,6 +179,10 @@
                                         # in kilobytes, or -1 for no limit
 
 #file_copy_method = copy                # copy, clone (if supported by OS)
+#file_extend_method = posix_fallocate   # the default is the first option supported
+                                        # by the operating system:
+                                        #   posix_fallocate (most Unix-like systems)
+                                        #   write_zeros
 
 #max_notify_queue_pages = 1048576       # limits the number of SLRU pages allocated
                                         # for NOTIFY / LISTEN queue

diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
index 413233bcd39d6c60df38d49404202715baf58ea6..8ac466fd3469af2498163bee631b7444d702af57 100644 (file)
--- a/src/include/storage/fd.h
+++ b/src/include/storage/fd.h
@@ -55,12 +55,23 @@ 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()