![]() ![]() I've had good experiences with Postgres in the past, so it seemed promising. Next, I tried out TimescaleDB, a Postgres extension for time series data. I decided not to play around with InfluxDB more today, because I already use it fairly often at work. It would be interesting to rewrite the import script in a lower level language like Rust or Go and see how it compares. Running the import script without actually connecting to InfluxDB was projected at about 2 hours, so it's entirely plausible that the majority of the overhead was on the Python side of things. I began importing the data into InfluxDB using a simple script built on influxdb-python, but stopped after I realized it was going to take about 10 hours to run (5k records/sec ingestion rate). My goal today, however, was to try out some time series databases. Use SMART data to predict future drive failures.The failure rate can then be taken into account when calculating the lifetime cost of a storage array. Calculate the reliability of different drives.A couple potential uses for this dataset: The SMART data is relatively sparse - most drive models only report a few SMART attributes. The model and capacity are given, as well as a large array of SMART attributes. The data files are in CSV format and contain one row per day per drive. While it might not seem like something a non-Backblaze user would be interested in, these failure rate statistics are very useful in determining which drives to invest in for home or office use, especially for photographers who regularly have to expand storage in order to accommodate growing image libraries.Backblaze publishes quarterly hard drive statistics. If you are interested in deep diving into all of the data collected, you can visit all previous Backblaze reports, ranging from 2013, on their statistics page. Since then, particular attention was paid to improving supply strategies. ![]() Although such extreme implications, like those experienced due to the global pandemic, couldn’t have been predicted, Backblaze had already gone through a supply chain disruption in 2011 when severe flooding affected Thailand. This particular tactic helped the company to navigate the market needs and limitations during a global pandemic. Overall, regardless of the drive capacity or its age, the improvements were visible throughout the entire range of different hard drive models in 2020.īackblaze set a goal at the start of 2020 to diversify the drive models it offered, which came in useful later on when COVID-19 began affecting the world economy and consequently the supply chain. On the other hand, 30,000 larger drives were added to the list - of capacities 14TB, 16TB, and 18TB - and as a group, they too improved to achieve 0.89% AFR. So while Seagate led the way, just about everyone saw marked improvements.īackblaze describes the notable improvement of AFR across the board as “a group effort.” On one hand, older drives as a group - which consists of 4TB, 6TB, 8TB, and 10TB capacity drives - improved in 2020 by going from 1.35% AFR in the year prior to 0.96% AFR. An improvement compared to the year prior, the AFR for all of the models included in the 2020 report was 0.93% which was less than half the AFR for 2019 which stood at 1.89%. “While each drive model has only been installed for about two months, they are off to a great start.”Ĭlose runners up to Seagate were two HGST 4TB drives (models HMS5C4040ALE640 and HMS5C4040BLE640) with 0.27% AFR, followed by the 8TB drive (model HUH728080ALE600) at 0.29% AFR, and the 12TB drive (model HUH721212ALE600) at 0.31% AFR. “The new Toshiba 14TB drive (model: MG07ACA14TA) and the new Toshiba 16TB (model: MG08ACA16TEY) were introduced to our data centers in 2020 and they are putting up zeros, as in zero failures,” the company writes. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |