![]() ![]() For specific numbers, Backblaze says that large drives “total 66% of the drive days total, while only producing 57% of the drive failures. That could point to problems for the average consumer, who is less likely to need a drive above 12TB in capacity, but it’s also worth pointing out that Backblaze’s larger drives were also newer. Overall, failure rates were low, with an average AFR of 1.01% across all drives, although smaller drives (those below 12TB) made up the majority of issues. On the other hand, HGST’s 4TB consumer hard. What does this all mean for hard drive storage in 2021 overall? Backblaze has now recorded and saved daily hard drive statistics from the drives in their data centers for over four years which is one of the most extensive. These drives had comparable Drive Days and Drive Count in Backblaze’s Q3 2017 report, in which they had higher failure rates of 3.28 and 18.85. Similarly, its 16TB Toshiba additions are also off to a strong start. Specifically, the 16TB WDC drive collection it added this year has only been in the fleet for an average of 5.06 months but has a low AFR of 0.14%. ![]() While Backblaze’s oldest drive was also its most stable, the company’s data also suggests that newer drives are holding up well. You can check yourself: Divide the failure count by the drive days to get a daily failure rate, then multiply by 365.25 and you will get the annualized failure rate. Regardless, if you’re curious, the formula for calculating AFR is as follows: AFR = (drive failures / (drive days/365)) * 100. One of the knocks on Backblaze is that its report covers its entire inventory, and comparing a brand-new 12TB drive to a 4TB drive that has been in deployment for a few years isn’t exactly fair. This, overall, provides a more accurate picture, making sure that new, unfailing drives added in Q4 don’t make a model look more reliable than it otherwise might have. ![]() Its data sheets refer to these with a term called “AFR,” which stands for “annualized failure rate.” This is slightly different from “annual failure rate,” in that it adjusts the data to account for drives which were added to or removed from the fleet partway through the year. You will also want to make sure that you have the correct drives selected for backup, this can be done by launching the Backblaze application, and clicking settings. Since 2013, Backblaze has published statistics and insights based on the hard drives in our data center. Before we move on, it’s important to address how Backblaze counts failure rates. When a files fingerprint matches an already backed up file, but its renamed or moved (including drive to drive), its simply updated at the servers, rather than re-transmitted. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |