News: 1663074116

  ARM Give a man a fire and he's warm for a day, but set fire to him and he's warm for the rest of his life (Terry Pratchett, Jingo)

Backblaze thinks SSDs are more reliable than hard drives

(2022/09/13)


Cloudy backup and storage provider Backblaze has found that flash SSDs are more reliable than hard drives, at least as far as the boot drives deployed in its datacenters go, but cautions this could change in future as the SSDs age.

These findings come from Backblaze's latest report detailing reliability statistics on the drives used in its infrastructure, and in this case it is only the second such report to focus on SSDs, following one [1]the company published in March .

One of the issues the company wanted to settle is whether SSDs really are more dependable than hard drives, but the data published in March appeared to show that the SSDs were following the same pattern of failure rate as the HDDs over time, albeit with a slightly lower annualized failure rate (AFR).

[2]

The SSDs and HDDs here are all used as boot drives, rather than the disks used to store data, and Backblaze began a switch to SSDs in Q4 2018, which means that the two sets of drives are at different points in their respective life expectancy curves. To compensate for this, the company only compared SSDs that were on average one year old with HDDs that were on average one year old, and so on.

[3]

With another year of data available, the failure rate of the SSDs took a downward turn rather than continuing to follow the same failure rate as the HDDs.

[4]

"At this point we can reasonably claim that SSDs are more reliable than HDDs, at least when used as boot drives in our environment. This supports the anecdotal stories and educated guesses made by our readers over the past year or so," said Andy Klein, Backblaze principal cloud storage evangelist.

However, he warned it is "highly certain" that the failure rate of the SSDs will eventually start to rise again, and it is possible that at some point the SSDs Backblaze uses could "hit the wall" perhaps when they start to reach their media wearout limits.

[5]

[6]

"Over the coming months we'll take a look at the SMART stats for our SSDs and see how they relate to drive failure. We also have some anecdotal information of our own that we'll try to confirm on how far past the media wearout limits you can push an SSD," Klein said.

The boot drives do more than just boot up Backblaze's storage servers, of course, as they also store log files and temporary files produced by each server, and so a boot drive will read, write, and delete files depending on the activity of the storage server itself.

[7]Yes, it's true: Hard drive failures creep up as disks age

[8]Backblaze report finds SSDs as reliable as HDDs

[9]Toshiba reveals 30TB disk drive to arrive by 2024

[10]Back up for a minute – Backblaze HD reliability stats show oldies can be goodies

As of June 30, 2022, there were 2,558 SSDs in the storage servers. This compares to the 2,200 SSDs that were covered in the March report.

Looking over the quarterly failure rates for Q1 and Q2 2022, it can be seen from the respective tables that the same number of failures was recorded (7) in each quarter, despite there being more drives included in Q2 than in Q1. This is reflected in the lower AFR for Q2 than for Q1.

[11]

Klein said that for any drive model within this cohort of SSDs, Backblaze would prefer to see it represented by at least 100 drives and account for at least 10,000 drive-days (the number of days all the drives of a specific model were operational) in a given quarter before considering the calculated AFR to be "reasonable." None of the drives meet this threshold yet.

Backblaze also examined the entire lifetime data available for all the SSD models it had active in its datacenters as at the end of Q2 2022.

[12]

It found that this lifetime AFR for all of the SSDs came out at 0.92 percent, a figure that is down from the 1.04 percent for the whole of 2021, but exactly the same as the Q2 2021 AFR of 0.92 percent. Klein warned here that Backblaze likes to see a confidence interval of 1 percent or less between the low and the high confidence interval values before the company is confident about the calculated AFR.

He noted that in these figures there are three drives with a confidence interval of 1 percent or lower, and picks out the Dell drive as the best.

[13]

"It is a server-class drive in an M.2 form factor, but it might be out of the price range for many users as it currently sells from Dell for $468.65," he commented. In contrast, the other two drives are consumer-focused and ship in the traditional SSD form factor, and both are from Seagate – the ZA250CM10003 and ZA250CM10002.

As ever, Backblaze makes available the data collected and analyzed for this report on its Hard Drive Test Data page for others to examine. Anyone can download and use this data for free, provided they cite Backblaze as the source and do not sell this data to others. ®

Get our [14]Tech Resources



[1] https://www.theregister.com/2022/03/04/backblaze_ssd_stats/

[2] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/storage&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2YyCpFwbTBDhx9Fn4djQkuAAAAI8&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0

[3] https://regmedia.co.uk/2022/09/12/backblaze-1.jpg

[4] https://regmedia.co.uk/2022/09/12/backblaze-2.jpg

[5] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/storage&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YyCpFwbTBDhx9Fn4djQkuAAAAI8&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[6] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/storage&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YyCpFwbTBDhx9Fn4djQkuAAAAI8&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0

[7] https://www.theregister.com/2022/08/03/hard_drive_failure_rate/

[8] https://www.theregister.com/2022/03/04/backblaze_ssd_stats/

[9] https://www.theregister.com/2022/02/09/30tb_toshiba_disk_drive/

[10] https://www.theregister.com/2022/02/01/backblaze_hd_reliability_stats_show/

[11] https://regmedia.co.uk/2022/09/12/backblaze-3.jpg

[12] https://regmedia.co.uk/2022/09/12/backblaze-4.jpg

[13] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/storage&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YyCpFwbTBDhx9Fn4djQkuAAAAI8&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[14] https://whitepapers.theregister.com/



Kev99

Obviously, Backblaze has yet needed to recover any data from an SSD. It's nearly impossible as I learned the hard way.

phuzz

If you're at the stage of trying to recover data from dead media, then several other things have gone wrong already. Such as RAID and backups.

(Although, as these are boot drives, I wouldn't be surprised if they're not backed up per se , but instead Backblaze have a procedure for rebuilding on a fresh drive, as if it was a brand new server)

Grooke

It's a valid concern for consumer usage, but yeah disk recovery is likely out-of-scope for Backblaze's usage.

Maybe

Francis Boyle

they know of a good backup service.

Seriously any data that's stored in only one place, on whatever medium, might as well not exist.

Potemkine!

Very interesting to have actual data. Sounds logical as there are no physical failure expected in a SSD.

Aren't also SSD limited in number of write/erase cycles?

== Bring us Dabbsy back! ==

Grooke

That's what they're referring too with "media wearout limit". That's the next thing then want to study

"we'll try to confirm on how far past the media wearout limits you can push an SSD"

Filippo

They are, but if these are boot disks, they probably don't get written to very much.

SSD is still a physical storage device

JoeCool

There certainly can be failures of the electronics circuits. As well as physical and mechanical stress caused by the environment.

43300

Assuming these are VM hosts, the usage on the boot drive with many hypervisors (e.g. ESXi) is going to be pretty light.

Hyper-V Server (or the Hyper-V role on Server Core) would be heavier, but I rather doubt if they are using those.

elwe

I doubt very many of these are hypervisors. When you run a scale out service you tend to use many whole boxes as service nodes, with no need for a hypervisor on most boxes. Typically you do have a very small number of hypervisors to run VMs for DNS, LDAP directories, sysog servers and other ancillary services.

These guys deserve a Nobel for "Science you can use"

JoeCool

I've been reading their reports for years - such good discussion.

*** NEWS FLASH ***

Archeologists find PDP-11/24 inside brain cavity of fossilized dinosaur
skeleton! Many Digital users fear that RSX-11M may be even more primitive
than DEC admits. Price adjustments at 11:00.