Re: WAL Performance Improvements

On Tue, 26 Feb 2002, Janardhana Reddy wrote:
> SUMMARY :
>
> Test1: (data_size= 8192 , with test program)
> fdatasync time +write time: 3141+46 = 3187 usec/call
> Time taken for 10000 iterations: nearly 40 seconds
> Test2 : (data_size = 160, with test program)
> fdatasync time+write time: 396 +13 = 409 usec/call
> Time taken for 10000 iterations: nealy 4 seconds

This only shows that your harddisk is doing write caching, although it
claims it does not (And on such systems I am tempted to say you can
turn off fsync unconditionally as it will gain you almost nothing).

Please look at the numbers: It is really *impossible* for any harddisk to
write to the same location more than 2000 times per second - simply due to
the fact that the disks are not rotating that fast. The fact that turning
writing caching on or off does not make a difference should make you
suspicious.

(In fact looking more closely at the numbers I am tempted to bet that you
operate your IDE disk in PIO mode: 1024bytes/400usec= 8192bytes/3200usec=
2.5MByte/s, and all you are benchmarking is the PIO transfer rate of your
IDE-controller/CPU combination).

This is not to say that your WAL optimization is worthless, but the
benchmark you gave is certainly wrong.

Regards
--
Helge Bahmann <bahmann(at)math(dot)tu-freiberg(dot)de> /| \__
Network admin, systems programmer /_|____\
_/\ | __)
$ ./configure \\ \|__/__|
checking whether build environment is sane... yes \\/___/ |
checking for AIX... no (we already did this) |