Backblaze published stats on SSD vs HDD reliability
-
Are SSDs Really More Reliable Than Hard Drives?
Solid-state drives (SSDs) continue to become more and more a part of the data storage landscape. And while our SSD 101 series has covered topics like upgrading, troubleshooting, and recycling your SSDs, we’d like to test one of the more popular declarations from SSD proponents: that SSDs fail much less often than our old friend, the hard disk drive (HDD). This statement is generally attributed to SSDs having no moving parts and is supported by vendor proclamations and murky mean time between failure (MTBF) computations. All of that is fine for SSD marketing purposes, but for comparing failure rates, we prefer the Drive Stats way: direct comparison. Let’s get started.
-
Great article!
-
@jaredbusch said in Backblaze published stats on SSD vs HDD reliability:
Are SSDs Really More Reliable Than Hard Drives?
Solid-state drives (SSDs) continue to become more and more a part of the data storage landscape. And while our SSD 101 series has covered topics like upgrading, troubleshooting, and recycling your SSDs, we’d like to test one of the more popular declarations from SSD proponents: that SSDs fail much less often than our old friend, the hard disk drive (HDD). This statement is generally attributed to SSDs having no moving parts and is supported by vendor proclamations and murky mean time between failure (MTBF) computations. All of that is fine for SSD marketing purposes, but for comparing failure rates, we prefer the Drive Stats way: direct comparison. Let’s get started.
Interesting read but unfortunately they don't have enough SSDs and have not had them long enough to draw any real conclusions.
And their use case is for boot drives - which isn't really applicable to normal server workloads. And they likely use lower spec consumer SSDs too which makes it even harder to draw any conclusions for servers where you normally see standard enterprise SSDs.
But it's good that Backblaze publish the data they have!
-
@pete-s said in Backblaze published stats on SSD vs HDD reliability:
And their use case is for boot drives
Umm, no it is not.
-
@pete-s said in Backblaze published stats on SSD vs HDD reliability:
Interesting read but unfortunately they don't have enough SSDs and have not had them long enough to draw any real conclusions.
And their use case is for boot drives - which isn't really applicable to normal server workloads. And they likely use lower spec consumer SSDs too which makes it even harder to draw any conclusions for servers where you normally see standard enterprise SSDs.They made that clear, and were up front about it.
The other factor we listed was drive days, the number of days all the drives in each cohort have been in operation without failing. The wide disparity in drive days causes a big difference in the confidence intervals of the two cohorts as the number of observations (i.e. drive days) varies significantly.Your response makes it look like you are disputing the article. I don't see anything disappointing at all in that article. They made it perfectly clear this is what they know now, based on different drive day cohorts. Then they said it would be a a couple of years before they had enough data to form a more clear understanding.
Over the next couple of years, as we get a better idea of SSD failure rates, we will be able to decide whether or not to add the AFR to the SSD versus HDD buying guide checklist.They never mentioned a use case, only a test case. And they explain why they think the boot drives are a reasonable measure of the drive in the real work load.
In our case, describing these drives as boot drives is a misnomer as boot drives are also used to store log files for system access, diagnostics, and more. In other words, these boot drives are regularly reading, writing, and deleting files in addition to their named function of booting a server at startup. -
@jasgot said in Backblaze published stats on SSD vs HDD reliability:
drive day cohorts.
And, the cohort is the storage stuff, not the boot drives. It was all very clearly noted as you say.
-
@jasgot said in Backblaze published stats on SSD vs HDD reliability:
Your response makes it look like you are disputing the article. I don't see anything disappointing at all in that article. They made it perfectly clear this is what they know now, based on different drive day cohorts. Then they said it would be a a couple of years before they had enough data to form a more clear understanding.
No, I'm not disputing it. I'm just wishing it was more.
We made the switch to SSD boot drives back in 2008-2009. And soon after that SSDs for all data. Since then I've only ever used 3.5" HDDs for large storage arrays.
-
It's still not even close to being a concise article. The only real metric there being discussed is simply age?
Maybe the SSDs moved 100x the data in their much shorter age so far? That would mean a lot and change the outcome significantly.
