Also what does a statspack of the two databases doing the benchmark show.
Jim
--
Replace part of the email address: kennedy-down_with_spammers_at_attbi.com
with family. Remove the negative part, keep the minus sign. You can figure
it out.
"Angus Fong" <angus_fong_at_hotmail.com> wrote in message
news:2db6dc80.0306091135.39fb46bf_at_posting.google.com...
> Hi,
>
> ok, I know it is not a apple - apple comparsion. But still, I am under
> pressure to give an 'answer'
> what I dont dont understatnd is, the Solarix box, better disk
> subsystem why is it running slower with insert. Personally, I do
> expect the Solaris box give a 10%/20% better result because it is
> running Raid 0+1 and it have more disks 22 in total.
>
> anyone can give me a hand, please
> thx, Angus
>
>
>
> "Noons" <wizofoz2k_at_yahoo.com.au.nospam> wrote in message
news:<3ee43984$1$8986$afc38c87_at_news.optusnet.com.au>...
> > "Angus Fong" <angus_fong_at_hotmail.com> wrote in message
> > news:2db6dc80.0306081947.1116d2b9_at_posting.google.com...
> >
> > >
> > > Windows NT 4.0, IBM netfinity, 4xP4 CPUs, 2G memeory, Raid5 only
> > > ~3300 rows/second
> >
> >
> > You cannot make RAID5 native in NT. You MUST be using
> > a dedicated RAID5 controller, which will probably have
> > a bucketfull of cache. And that means you can't compare
> > both. Where are your redo logs? How fast are the P4 CPUs?
> >
> > >
> > > Solaris 5.8, 420R, 4 CPUs, 4G memory, RAID 0,1 (raw devices)
> > > ~2700 rows/second
> >
> > Are you using Sun's LVM to create the RAID0,1 devices?
> > If so, why are you using raw? You should be using raw
> > in your redo logs, but you do NOT need to make your data
> > tablespace raw to get max performance.
> > How fast is the SUN CPU? How many 0,1 devices you using
> > and how many db writers?
> >
> > >
> > > Solaris 5.8, 6800, 6 processors board, 4G memory, RAID 0,1 (raw
> > > devices)
> > > ~2500 rows/second
> > >
> >
> > Same comments as before.
Received on Mon Jun 09 2003 - 21:57:38 CDT
