Thread: Re: [HACKERS] fsync method checking

Kurt Roeckx wrote:
> Here are my results on Linux 2.6.1 using cvs version 1.7.
>
> Those times with > 20 seconds, you really hear the disk go crazy.
>
> And I have the feeling something must be wrong.  Those results
> are reproducible.
>

Wow, your O_SYNC times are great.  Where can I buy some?  :-)

Anyway, we do need to find a way to test this because obviously there is
huge platform variability.

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


>
> Kurt
>
>
> Simple write timing:
>         write                    0.139558
>
> Compare fsync times on write() and non-write() descriptor:
> (If the times are similar, fsync() can sync data written
>  on a different descriptor.)
>         write, fsync, close      8.249364
>         write, close, fsync      8.356813
>
> Compare one o_sync write to two:
>         one 16k o_sync write    28.487650
>         two 8k o_sync writes     2.310304
>
> Compare file sync methods with one 8k write:
>         (o_dsync unavailable)
>         open o_sync, write       1.010688
>         write, fdatasync        25.109604
>         write, fsync,           26.051218
>
> Compare file sync methods with 2 8k writes:
> (The fastest should be used for wal_sync_method)
>         (o_dsync unavailable)
>         open o_sync, write       2.212223
>         write, fdatasync        27.439907
>         write, fsync,           27.772294
>
>
> ---------------------------(end of broadcast)---------------------------
> TIP 5: Have you checked our extensive FAQ?
>
>                http://www.postgresql.org/docs/faqs/FAQ.html
>

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

On Thu, Mar 18, 2004 at 03:34:21PM -0500, Bruce Momjian wrote:
> Kurt Roeckx wrote:
> > Here are my results on Linux 2.6.1 using cvs version 1.7.
> >
> > Those times with > 20 seconds, you really hear the disk go crazy.
> >
> > And I have the feeling something must be wrong.  Those results
> > are reproducible.
> >
>
> Wow, your O_SYNC times are great.  Where can I buy some?  :-)
>
> Anyway, we do need to find a way to test this because obviously there is
> huge platform variability.

New results with version 1.8:

Simple write timing:
        write                    0.150613

Compare fsync times on write() and non-write() descriptor:
(If the times are similar, fsync() can sync data written
 on a different descriptor.)
        write, fsync, close      9.170472
        write, close, fsync      8.851715

Compare one o_sync write to two:
        one 16k o_sync write     2.617860
        two 8k o_sync writes     2.563437

Compare file sync methods with one 8k write:
        (o_dsync unavailable)
        open o_sync, write       1.031721
        write, fdatasync        25.599010
        write, fsync,           26.192824

Compare file sync methods with 2 8k writes:
(The fastest should be used for wal_sync_method)
        (o_dsync unavailable)
        open o_sync, write       2.268718
        write, fdatasync        27.029396
        write, fsync,           27.399243