Hard drive failures

[[TC]»Elmo«]

(2012-11-24 00:12)Pipa Wrote:  Read that study aswell, but it only said that very low or very high temperatures had a negative effect on the durability. After all google uses these drives 24/7 which means over time there will be small temperature changes and as 30°C+ isn't killing them it could be the change of the temperature that might be a harming factor.

Not quite...

Quote:We first look at the correlation between average temperature during the observation period and failure. Figure 4 shows the distribution of drives with average temperature in increments of one degree and the corresponding annualized failure rates. The figure shows that failures do not increase when the average temperature increases. In fact, there is a clear trend showing that lower temperatures are associated with higher failure rates. Only at very high temperatures is there a slight reversal of this trend.

37°-45° Has the lowest failure rate (~1%)
30° is 2%
25° is 3%
20° is about 7%, but they had fewer drives that cool, so the distribution is a bit bigger.

They did show that older drives (3+ years) had higher fail rates (only up to about 2x though) at higher temperatures (>40°), but as it was a 9 month study, it's unclear whether that's to do with actual age or older technology.

Overall, looks like the sweet spot over the life of the drive is ~35°

They also acknowledged other studies which showed that changes in temperature of >15° can double the failure rate. However, they weren't clear if they meant operating temperatures or whether they were including initial warm-up time, although I'd guess it's operating temp.