On 23 Nov 2008 21:27:02 -0800, [EMAIL PROTECTED] (Ed Gould) wrote: >I was astounded to see that Google now claims to sort 6 petabytes in a few >hours. This is astounding. I bet Frank Yeager would be interested in this, I >know we could never come close to this in the mainframe world. I am in >complete awe of this. It is not clear exactly what they are sorting >unfortunately but if it is even half true the sort on the mainframe may be >passed its prime and showing its age.
Google has some different requirements, which may or may not have a bearing on this result - dropped records are not unacceptable, for instance. When you do a search going through one machine you are likely to find different results than when you do a search going through another machine. It works for them. ---------------------------------------------------------------------- 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
