pg_fallocate
Hi,
I'l like to add fallocate() system call to improve sequential read/write
peformance. fallocate() system call is different from posix_fallocate()
that is zero-fille algorithm to reserve continues disk space. fallocate()
is almost less overhead alogotithm to reserve continues disk space than
posix_fallocate().
It will be needed by sorted checkpoint and more faster vacuum command in
near the future.
If you get more detail information, please see linux manual.
I go sight seeing in Dublin with Ishii-san now:-)
Regards,
--
Mitsumasa KONDO
NTT Open Source Software
Attachments:
pg_fallocate_v0.patchapplication/octet-stream; name=pg_fallocate_v0.patchDownload
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 06f5eb0..340e0fd 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -3408,7 +3408,9 @@ XLogFileInit(XLogSegNo logsegno, bool *use_existent, bool use_lock)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not create file \"%s\": %m", tmppath)));
-
+#if defined(HAVE_FALLOCATE)
+ fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, XLogSegSize);
+#endif
/*
* Zero-fill the file. We have to do this the hard way to ensure that all
* the file space has really been allocated --- on platforms that allow
diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index de4d902..afa3d24 100644
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -383,6 +383,21 @@ pg_flush_data(int fd, off_t offset, off_t amount)
return 0;
}
+/*
+ * pg_fallocate --- advise OS that the data pre-allocate continus file segments
+ * in physical disk.
+ *
+ * Not all platforms have fallocate. Some platforms only have posix_fallocate,
+ * but it ped zero fill to get pre-allocate file segmnets. It is not good
+ * peformance when extend new segmnets, so we don't use posix_fallocate.
+ */
+int
+pg_fallocate(File file, int flags, off_t offset, off_t nbytes)
+{
+#if defined(HAVE_FALLOCATE)
+ return fallocate(VfdCache[file].fd, flags, offset, nbytes);
+#endif
+}
/*
* fsync_fname -- fsync a file or directory, handling errors properly
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index e629181..fe6f640 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -24,6 +24,7 @@
#include <unistd.h>
#include <fcntl.h>
#include <sys/file.h>
+#include <linux/falloc.h>
#include "miscadmin.h"
#include "access/xlog.h"
@@ -510,6 +511,10 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
* if bufmgr.c had to dump another buffer of the same file to make room
* for the new page's buffer.
*/
+
+ if(forknum == 1)
+ pg_fallocate(v->mdfd_vfd, FALLOC_FL_KEEP_SIZE, 0, RELSEG_SIZE);
+
if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
ereport(ERROR,
(errcode_for_file_access(),
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 5eac52d..43d8eaf 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -146,6 +146,9 @@
/* Define to 1 if you have the <editline/readline.h> header file. */
#undef HAVE_EDITLINE_READLINE_H
+/* Define to 1 if you have the 'fallocate' function. */
+#undef HAVE_FALLOCATE
+
/* Define to 1 if you have the `fdatasync' function. */
#undef HAVE_FDATASYNC
diff --git a/src/include/pg_config.h.win32 b/src/include/pg_config.h.win32
index 54db287..b8643fc 100644
--- a/src/include/pg_config.h.win32
+++ b/src/include/pg_config.h.win32
@@ -112,6 +112,9 @@
/* Define to 1 if you have the <editline/readline.h> header file. */
/* #undef HAVE_EDITLINE_READLINE_H */
+/* Define to 1 if you have the 'fallocate' function. */
+/* #undef HAVE FALLOCATE */
+
/* Define to 1 if you have the `fcvt' function. */
#define HAVE_FCVT 1
diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
index 2a60229..5ac1f6a 100644
--- a/src/include/storage/fd.h
+++ b/src/include/storage/fd.h
@@ -113,6 +113,7 @@ extern int pg_fsync_no_writethrough(int fd);
extern int pg_fsync_writethrough(int fd);
extern int pg_fdatasync(int fd);
extern int pg_flush_data(int fd, off_t offset, off_t amount);
+extern int pg_fallocate(File file, int flags, off_t offset, off_t amount);
extern void fsync_fname(char *fname, bool isdir);
/* Filename components for OpenTemporaryFile */
On Thu, Oct 31, 2013 at 9:16 AM, Mitsumasa KONDO
<kondo.mitsumasa@gmail.com> wrote:
I'l like to add fallocate() system call to improve sequential read/write
peformance. fallocate() system call is different from posix_fallocate() that
is zero-fille algorithm to reserve continues disk space. fallocate() is
almost less overhead alogotithm to reserve continues disk space than
posix_fallocate().It will be needed by sorted checkpoint and more faster vacuum command in
near the future.If you get more detail information, please see linux manual.
I go sight seeing in Dublin with Ishii-san now:-)
Our last attempts to improve performance in this area died in a fire
when it turned out that code that should have been an improvement fell
down over inexplicable ext4 behavior. I think, therefore, that
extensive benchmarking of this or any other proposed approach is
absolutely essential.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
On 10/31/13, 9:16 AM, Mitsumasa KONDO wrote:
I'l like to add fallocate() system call to improve sequential read/write
peformance. fallocate() system call is different from posix_fallocate()
that is zero-fille algorithm to reserve continues disk space.
fallocate() is almost less overhead alogotithm to reserve continues disk
space than posix_fallocate().
Your patch seems to be missing a bit that defines HAVE_FALLOCATE,
probably something in configure.in.
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
On Thu, Oct 31, 2013 at 01:16:44PM +0000, Mitsumasa KONDO wrote:
--- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -383,6 +383,21 @@ pg_flush_data(int fd, off_t offset, off_t amount) return 0; }+/* + * pg_fallocate --- advise OS that the data pre-allocate continus file segments + * in physical disk. + * + * Not all platforms have fallocate. Some platforms only have posix_fallocate, + * but it ped zero fill to get pre-allocate file segmnets. It is not good + * peformance when extend new segmnets, so we don't use posix_fallocate. + */ +int +pg_fallocate(File file, int flags, off_t offset, off_t nbytes) +{ +#if defined(HAVE_FALLOCATE) + return fallocate(VfdCache[file].fd, flags, offset, nbytes); +#endif +}
You should set errno to ENOSYS and return -1 if HAVE_FALLOCATE isn't
defined.
--- a/src/backend/storage/smgr/md.c +++ b/src/backend/storage/smgr/md.c @@ -24,6 +24,7 @@ #include <unistd.h> #include <fcntl.h> #include <sys/file.h> +#include <linux/falloc.h>
This would have to be wrapped in #ifdef HAVE_FALLOCATE or
HAVE_LINUX_FALLOC_H; if you want to create a wrapper around fallocate() you
should add PG defines for the flags, too. Otherwise it's probably easier to
just call fallocate() directly inside an #ifdef block as you did in xlog.c.
@@ -510,6 +511,10 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, * if bufmgr.c had to dump another buffer of the same file to make room * for the new page's buffer. */ + + if(forknum == 1) + pg_fallocate(v->mdfd_vfd, FALLOC_FL_KEEP_SIZE, 0, RELSEG_SIZE); +
Return value should be checked; if it's -1 and errno is something else than
ENOSYS or EOPNOTSUPP the disk space allocation failed and you must return an
error.
/ Oskari
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers