Per Ian Cutress quoting experts at the Data Centre World conference in London, no one wants SSDs with a capacity over 16TB per drive so it makes absolute sense that no one in their right mind will want that same sort of capacity in a mechanical drive. These cannot sell. These will not sell. No one wants more capacity or higher data densities. Go shove those 16+TB drives because nobody needs more storage space!
Disclaimer: If anyone has dead batteries in their sarcasm detector, the above remark is indeed sarcasm and does not warrant a reply interpreting it as a serious statement unless said seriously worded statement is also sarcasm. Thank you.
I think you misunderstand what Ian's reporting really was saying. Yes there is a need for capacity. No, given the price premium, the demand is not there for that capacity in solid state. I wish it were, my NAS would love a set of 8TB SSD's @200/each but it isn't happening anytime soon sadly..
Having to run 2x8TB vs 1x16TB increases your failure risk and thus the frequency of rebuilds. Plus the amount of data you have is the amount of data you have, rebuild time is the same either way.
Sounds like someone is a fan of 1 TB drives. Or maybe you're still buying 500 GB drives?
It is true that the time it takes to rebuild the data is long and there's some risk if you only have a single mirror of that drive when the failure occurs. But if your data storage is that important for sure you have a secondary site replicating the data anyway so this argument is moot.
While I think a 16 TB will scare a lot of companies I'm sure many business will find value in the drives as a legacy friendly upgrade option. After all while there are clear disadvantages like the hours(days?) it takes to replace failed drives it's a lot cheaper to buy bigger drives than new systems when you need more space.
I wouldn't mind some 16 TB drives for cold storage and mediaplex use if they are a. Not shingled and b. Cheap enough so I can buy them in pairs for redundancy.
Shingled magnetic recording? Pass! Heat assisted or not, shingled drives invite failure much more so than PMR and other approaches. Now, if anyone here can convince me otherwise with data and good arguments, please do so.
An 18TB drive failure... that's allot to rebuild in whatever RAID configuration you have.
I honestly hadn't expected folks to want to go much bigger than 16TB in one drive... just because of the amount of data at risk. But I guess folks have always said that as capacities have increased.
Funny... I've just read some of your comments.... and you've echoed the same sentiments... even glanced that AnandTech article that was referenced about huge single drive failure fears above 16B.
It's a silly concern. Yes, large drives take more time to rebuild. But that's about the data, and if you have to store this amount of data for any reason, it's going to be slow to rebuild whether its on large drive arrays or small drive arrays, but in the latter you've added more points of failure.
Wouldnt the edges of 5.25 HD spinning at 15000rpm go hypersonic? The deaths of four testing engineers at WD proved that ......buried in eight coffins !
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
25 Comments
Back to Article
s.yu - Monday, May 6, 2019 - link
Interesting...but more platters sound like more points of failure, especially as mechanical parts are shrunken down.StevoLincolnite - Tuesday, May 7, 2019 - link
And being a Seagate... You know failure rates will be higher than normal anyway.melgross - Monday, May 6, 2019 - link
It’s always possible that some of those HAMR components are just not ready yet. It doesn’t have to be client pushback, or cost.smilingcrow - Monday, May 6, 2019 - link
So it's not 'HAMR Time` yet! :)brunis.dk - Wednesday, May 8, 2019 - link
You can't touch this (comment)!PeachNCream - Monday, May 6, 2019 - link
Per Ian Cutress quoting experts at the Data Centre World conference in London, no one wants SSDs with a capacity over 16TB per drive so it makes absolute sense that no one in their right mind will want that same sort of capacity in a mechanical drive. These cannot sell. These will not sell. No one wants more capacity or higher data densities. Go shove those 16+TB drives because nobody needs more storage space!(Source: https://www.anandtech.com/show/14081/the-reality-o...
Disclaimer: If anyone has dead batteries in their sarcasm detector, the above remark is indeed sarcasm and does not warrant a reply interpreting it as a serious statement unless said seriously worded statement is also sarcasm. Thank you.
Reflex - Monday, May 6, 2019 - link
I think you misunderstand what Ian's reporting really was saying. Yes there is a need for capacity. No, given the price premium, the demand is not there for that capacity in solid state. I wish it were, my NAS would love a set of 8TB SSD's @200/each but it isn't happening anytime soon sadly..piroroadkill - Tuesday, May 7, 2019 - link
I'm pretty sure it's more to do with rebuild times. Larger drives without faster speeds equals more risk due to longer rebuild times.Reflex - Tuesday, May 7, 2019 - link
Having to run 2x8TB vs 1x16TB increases your failure risk and thus the frequency of rebuilds. Plus the amount of data you have is the amount of data you have, rebuild time is the same either way.BrianDuda - Monday, May 20, 2019 - link
Sounds like someone is a fan of 1 TB drives. Or maybe you're still buying 500 GB drives?It is true that the time it takes to rebuild the data is long and there's some risk if you only have a single mirror of that drive when the failure occurs. But if your data storage is that important for sure you have a secondary site replicating the data anyway so this argument is moot.
PixyMisa - Monday, May 6, 2019 - link
That report was saying that rather than 32TB SSDs, they wanted twice the number of 16TB SSDs in a smaller form factor.Skeptical123 - Monday, May 6, 2019 - link
While I think a 16 TB will scare a lot of companies I'm sure many business will find value in the drives as a legacy friendly upgrade option. After all while there are clear disadvantages like the hours(days?) it takes to replace failed drives it's a lot cheaper to buy bigger drives than new systems when you need more space.eastcoast_pete - Monday, May 6, 2019 - link
I wouldn't mind some 16 TB drives for cold storage and mediaplex use if they are a. Not shingled and b. Cheap enough so I can buy them in pairs for redundancy.Reflex - Monday, May 6, 2019 - link
SMR is pretty ideal for those scenarios. I use them in my NAS for storage and Plex very effectively.eastcoast_pete - Monday, May 6, 2019 - link
Shingled magnetic recording? Pass! Heat assisted or not, shingled drives invite failure much more so than PMR and other approaches. Now, if anyone here can convince me otherwise with data and good arguments, please do so.phoenix_rizzen - Monday, May 6, 2019 - link
The 16 TB drives detailed in this article are PMR.The 18 TB drives will first be SMR, then later PMR as HAMR/PAMR/MAMR and similar technologies improve.
Reflex - Monday, May 6, 2019 - link
Where are you seeing failure data for SMR?piroroadkill - Wednesday, May 8, 2019 - link
It's literally in the title that this 16TB drive is NOT shingledHardwareDufus - Monday, May 6, 2019 - link
An 18TB drive failure... that's allot to rebuild in whatever RAID configuration you have.I honestly hadn't expected folks to want to go much bigger than 16TB in one drive... just because of the amount of data at risk. But I guess folks have always said that as capacities have increased.
HardwareDufus - Monday, May 6, 2019 - link
Funny... I've just read some of your comments.... and you've echoed the same sentiments... even glanced that AnandTech article that was referenced about huge single drive failure fears above 16B.Reflex - Monday, May 6, 2019 - link
It's a silly concern. Yes, large drives take more time to rebuild. But that's about the data, and if you have to store this amount of data for any reason, it's going to be slow to rebuild whether its on large drive arrays or small drive arrays, but in the latter you've added more points of failure.rpg1966 - Monday, May 6, 2019 - link
Lol, at every new step up in drive capacity since ever, there's always someone who makes this comment.rpg1966 - Monday, May 6, 2019 - link
Just to be pedantic, it's "a lot"."Allot" is a different word altogether.
mikegrok - Thursday, May 9, 2019 - link
I used to have a 19 platter, and a 21 platter 5 1/4 inch full height drive (one of them was 2.7 GB).Think how much capacity those would have with today's areal densities.
dromoxen - Friday, May 10, 2019 - link
Wouldnt the edges of 5.25 HD spinning at 15000rpm go hypersonic? The deaths of four testing engineers at WD proved that ......buried in eight coffins !