On Mon, Apr 6, 2009 at 3:20 AM, John Hearns <hear...@googlemail.com> wrote: > 2009/4/6 Rahul Nabar <rpna...@gmail.com>: >> We had bought 23 Dell-SC1435-PowerEdge servers for our latest cluster >> addition mid-2008. These batch of machines has proved to be a total >> disaster from Day one. I was looking for suggestions how I should >> tackle this. > > Sending an email to an international email list composed of people who > make purchasing decisions > for future machines costing many thousands of $$$$ is an excellent start! > > Seriously - I hope your Dell account manager sees this and starts kicking > butt.
Thanks Joe! One of the biggest problems in a huge setup like Dell's is the lack of a clear incentive to help me. The tech-services guy isn't the one who's making money on the next order. Actually each time you almost start speaking to a new person so rarely do you find a rep. wanting to take the courageous decision of deciding it is indeed a bad system and swapping it (or alternatively spending hours in a truly out-of-the-box debug cycle to diagnose what exactly the bad component is). Most merely prolong the cycle by mindless testing and running of sosreports and dsets and such. Some create even more activity by asking me to change distros and sending me a CPU here and a power-supply there in the hopes that something will work! -- Rahul _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
