Re: 2-node RAC faster than 6-node!
Date: Fri, 04 Apr 2008 14:52:31 +0400
That is not completely right. In addition to "transfer path" (2-|3-way)
there might be such a thing like the
"queue to resource master". I mean, that if many/all instances have a need in one and the same block,
they first go to resource master. And while the master is surving the first request, the others are in the queue. The more nodes, the longer the queue is, and a queuing theory comes into play here.
Of course, in this case of s... happens the application should be quite unscalable...
Dan Norris wrote:
> I suppose that there may be some difference between 4 and 6 nodes with
> respect to the occurrence of 2 vs 3-way block negotiations. However, I
> don't think that will be a noticeable. I think the only time you'd
> have enough impact to really measure the difference would be between 2
> and 3 nodes and that's supported by the study I mentioned (that I
> still can't seem to locate).