I saw that plot in the CERN Tier0 talk at GridPP27, but the end of life
failures were purely hypothetical as it only showed 3 years of data.
Would love to see that curve with actual data beyond 5 years - does RAL
Ewan MacMahon wrote:
>> -----Original Message-----
>> From: Testbed Support for GridPP member institutes [mailto:TB-
>> [log in to unmask]] On Behalf Of Andrew Sansum
>> On a big installation like this, its necessary to keep a close watch on
>> generation related issues as things can rapidly go pear shaped. Moving a
>> generation out of production at short notice (and plugging the gap in
>> capacity) is not trivial.
> I recall someone from CERN showing off a graph of failure rate
> against age that they described as 'bath tub' shaped - high at
> the start, then dropping off to remain level for a while, then
> swinging back up again towards the end.