OK - here's another link - http://www.theregister.co.uk/2006/05/04/google_bigdaddy_chaos/
It seems that everyone insists on reinventing wheels. Apart from anything else, this is a classic capacity planning failure. I wonder what would happen to any zSeries capacity planner whose work was so bad that the CEO had to apologise in the New York Times? Google might have gotten lots of cheap MIPS on its distributed platforms, but it obviously didn't get the scalability it requires and now it has a computing system that can't keep up with its business plan. When was the last time this happened to a zSeries user? Scalability? I think that's one of the boxes zSeries can tick. As regards how useful Google's search results are, they're not. As a webmaster I can promise you from my logs that Google is about five weeks behind updating its indices - stuff I notified them of on 28th/29th March was being downloaded yesterday. MSN, Yahoo, Ask and the others are keeping up hourly. Anyway, it's a headline failure for the "we can do anything with loads of little PCs" approach, and useful ammunition if someone suggests it. The closer an application is to business-critical, the more they should be careful. -- Phil Payne http://www.isham-research.co.uk +44 7833 654 800 ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
