Re: [HACKERS] win32 performance - fsync question

From: Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
To: Magnus Hagander <mha(at)sollentuna(dot)net>
Cc: Michael Paesold <mpaesold(at)gmx(dot)at>, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, pgsql-hackers-win32(at)postgresql(dot)org, Merlin Moncure <merlin(dot)moncure(at)rcsonline(dot)com>, PostgreSQL-patches <pgsql-patches(at)postgresql(dot)org>
Subject: Re: [HACKERS] win32 performance - fsync question
Date: 2005-03-24 04:31:15
Message-ID: 200503240431.j2O4VFG07349@candle.pha.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers pgsql-hackers-win32 pgsql-patches


I have applied the following patch to CVS HEAD and 8.0.X that changes
the Win32 O_SYNC flag to O_DATASYNC, because this the actual behavior of
the flag. This is now the default wal fsync method on Win32 because we
perfer O_DATASYNC to fsync().

And second, it changes Win32 fsync to a new wal sync method called
fsync_writethrough which is the old Win32 fsync behavior, which uses
_commit().

---------------------------------------------------------------------------

Magnus Hagander wrote:
> > > > > * Win32, with fsync, write-cache disabled: no data corruption
> > > > > * Win32, with fsync, write-cache enabled: no data corruption
> > > > > * Win32, with osync, write cache disabled: no data corruption
> > > > > * Win32, with osync, write cache enabled: no data
> > corruption. Once
> > > > > I
> > > > > got:
> > > > > 2005-02-24 12:19:54 LOG: could not open file "C:/Program
> > > > > Files/PostgreSQL/8.0/data/pg_xlog/000000010000000000000010"
> > > > (log file
> > > > > 0, segment 16): No such file or directory
> > > > > but the data in the database was consistent.
> > > >
> > > > It disturbs me that you couldn't produce data corruption in the
> > > > cases where it theoretically should occur. Seems like this is an
> > > > indication that your test was insufficiently severe, or
> > that there
> > > > is something going on we don't understand.
> > >
> > > The Windows driver knows abotu the write cache, and at
> > least fsync()
> > > pushes through the write cache even if it's there. This seems to
> > > indicate taht O_SYNC at least partiallyi does this as well. This is
> > > why there is no performance difference at all on fsync() with write
> > > cache on or off.
> > >
> > > I don't know if this is true for all IDE disks. COuld be
> > that my disk
> > > is particularly well-behaved.
> >
> > This indicated to me that open_sync did not require any
> > additional changes than our current fsync.
>
> fsync and open_sync both write through the write cache in the operating
> system. Only fsync=off turns this off.
>
> fsync also writes through the hardware write cache. o_sync does not.
> This is what causes the large slowdown with write cache enabled,
> *including* most battery backed write cache systems (pretty much making
> the write-cache a waste of money). This may be a good thing on IDE
> systems (for admins that don't know how to remove the little check in
> the box for "enable write caching on the disk" that MS provides, which
> *explicitly* warns that you may lose data if you enabled it), but it's a
> very bad thing for anything higher end.
>
> fsync also syncs the directory metadata. o_sync only cares about the
> files contents. (This is what causes the large slowdown with write cache
> *disabled*, becuase it requires multiple writes on multiple disk
> locations for each fsync).
>
>
> Basically, fsync hurts people who configure their box correctly, or who
> use things like SCSI disks. o_sync hurts people who configure their
> machine in an unsafe way.
>
> //Magnus
>
> ---------------------------(end of broadcast)---------------------------
> TIP 1: subscribe and unsubscribe commands go to majordomo(at)postgresql(dot)org
>

--
Bruce Momjian | http://candle.pha.pa.us
pgman(at)candle(dot)pha(dot)pa(dot)us | (610) 359-1001
+ If your life is a hard drive, | 13 Roberts Road
+ Christ can be your backup. | Newtown Square, Pennsylvania 19073

Attachment Content-Type Size
unknown_filename text/plain 6.1 KB

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Bruce Momjian 2005-03-24 05:15:53 Re: fool-toleranced optimizer
Previous Message Christopher Kings-Lynne 2005-03-24 01:03:04 Re: \x in psql

Browse pgsql-hackers-win32 by date

  From Date Subject
Next Message Andrew Sullivan 2005-03-24 13:17:49 Re: Simple query takes a long time on win2K
Previous Message A. Mous 2005-03-24 03:49:22 Re: Simple query takes a long time on win2K

Browse pgsql-patches by date

  From Date Subject
Next Message Bruce Momjian 2005-03-24 04:42:56 Link to pgport earlier
Previous Message Michael Fuhr 2005-03-24 04:23:43 Re: PL/Python patch for Universal Newline Support