A two-and-a-half year study of DRAM on 10s of thousands Google servers found DIMM error rates are hundreds to thousands of times higher than thought — a mean of 3,751 correctable errors per DIMM per year. This is the world’s first large-scale study of RAM errors in the field. It looked at multiple vendors, DRAM densities and DRAM types including DDR1, DDR2 and FB-DIMM.
This was a self-funded startup that a college friend and I worked on for a year and a half. We launched 3 websites in that time. It ended up going nowhere, but there seems to be a lot of folks asking for stories of startups that just fade away, so I made this blog public anyway.
