Re: [HACKERS] WAL Performance Improvements

On Tue, 2002-02-26 at 17:33, Janardhana Reddy wrote:
> Helge Bahmann wrote:
>
> > On Tue, 26 Feb 2002, Janardhana Reddy wrote:
> > > Test Results with Latest patch :
> > > environment: Intel PC ,IDE (harddisk),Linux Kernel 2.4.0 (OS
> > > Version). Single
> > > connection is connected to the database and pumping
> > > continously insert statements. each insert
> > > generates 160 bytes to WAL Log.
> >
> > 8192:
> > > Transaction Per Second : 332 TPS
> > > Time Taken by fdatasync : 2160
> >
> > 4096:
> > > Transaction Per Second : 435 TPS
> > > Time Taken by fdatasync : 512
> >
> > Unforunately your timings are meaningless. Assuming you have a
> > 10000rpm drive (that is, 166 rounds per second), it is physically
> > impossible to write 332 or 435 times per second to the same location
> > on the disk.

But it is possible to push data to disk cache and be pretty sure that it
will be written in next 1/166th of a second. Most modern disk should be
able to cache writes for at least one whole track and it makes sense to
report it as "written" when it is in write cache and disk is confident
that it will be written even if power failure happens the next moment.

--------------
Hannu