Re: SAME methodology opinions?

yong321_at_yahoo.com (Yong Huang) wrote in message news:<b3cb12d6.0303080723.5f3e2713_at_posting.google.com>...
> bchorng_at_yahoo.com (Bass Chorng) wrote in message news:<bd9a9a76.0303071653.41b5878a_at_posting.google.com>...
> > However, my honest opinion is, if you do not have real load
> > challenge, go ahead use SAME, even with RAID 5. For most sites
> > this just work fine. Chances are that your NVRAM will cover all
> > your wrong doings.
> >
> > If you expect to have real load challenge, then do all the
> > home work and plan your IO. I have seen sites that can only
> > survive this way.
>
> Could you elaborate on the NVRAM part? Thanks.
>
> Yong Huang

  Most SAN now-a-days has very large NVRAM. I think a   Hitachi 9980 can have 32 GB of NVRAM (thats mirrored).   Everything you write goes to the cache. At that point, it   really does not matter where you put your redo.

  Your IO is between OS kernel and the SAN cache. Whatever   happens between the cache and the actual disks usually does   not have anything to do with your performance.

  However, it does make a difference if either you do not have   a lot of cache (or cash) or/and your IO load is very high, as   your NVRAM could be saturated. Now, once it does, you will   have a very bad IO wait. This is especially prominant on an   EMC. In this case, if you plan your redo strategically   like everything Steve Adams suggested, then the saturation   is less likely to happen.

  As to RAID, I think some SANs (such as IBM Shark I believe)   only supports RAID5. They use large NVRAM and sophisticated   caching algorithem to cover the shortcomings of using RAID 5   (or 5+ with Hitachi) for OLTP.   

  My personal belief is the technology will eventually make   IO tuning less and less important, unless you have a very   extreme situation. Received on Mon Mar 10 2003 - 14:33:18 CST