Re: Performance large tables.

What kind of performance boost do you get from using raid 10? I am trying
to do a little cost analysis.

Benjamin Arai
barai(at)cs(dot)ucr(dot)edu
benjamin(at)cs(dot)ucr(dot)edu
http://www.benjaminarai.com

> -----Original Message-----
> From: pgsql-general-owner(at)postgresql(dot)org
> [mailto:pgsql-general-owner(at)postgresql(dot)org] On Behalf Of
> Franz(dot)Rasper(at)izb(dot)de
> Sent: Monday, December 12, 2005 11:50 PM
> To: vivek(at)khera(dot)org
> Cc: pgsql-general(at)postgresql(dot)org
> Subject: Re: [GENERAL] Performance large tables.
>
> Hello,
>
> may I ask you some questions.
>
> What is the performance difference between U320 15kRPM and
> U320 10kRPM ?
> Does your RAID crontoller has some memory (e.g. 128 MB or 256
> MB ) and something like memory backup write cache (like HP DL
> 380 server) ?
> Do you use Intel or Opteron cpus ?
>
> regards,
>
> -Franz
>
> -----Ursprüngliche Nachricht-----
> Von: Vivek Khera [mailto:vivek(at)khera(dot)org]
> Gesendet: Montag, 12. Dezember 2005 23:15
> An: PG-General General
> Betreff: Re: [GENERAL] Performance large tables.
>
>
>
> On Dec 10, 2005, at 6:37 PM, Benjamin Arai wrote:
>
> > For the most part the updates are simple one liners. I currently
> > commit in large batch to increase performance but it still takes a
> > while as stated above. From evaluating the computers performance
> > during an update, the system is thrashing both memory and
> disk. I
> > am currently using Postgresql 8.0.3.
>
> Then buy faster disks. My current favorite is to use U320 15kRPM
> disks using a dual-chanel RAID controller with 1/2 the disks on one
> channel and 1/2 on the other and mirroring them across
> channels, then
> striping down the mirrors (ie, RAID10).
>
> I use no fewer than 6 disks (RAID 10) for data and 2 for pg_log in a
> RAID1.
>
>
> ---------------------------(end of
> broadcast)---------------------------
> TIP 3: Have you checked our extensive FAQ?
>
> http://www.postgresql.org/docs/faq
>
> ---------------------------(end of
> broadcast)---------------------------
> TIP 4: Have you searched our list archives?
>
> http://archives.postgresql.org
>